docs(tools): enrich low-scoring tool descriptions for Glama TDQS#16
Merged
Conversation
Rewrite the 31 tool descriptions Glama scored at or below 4.0/5 (the lowest being rename_page/set_reactions/set_visible at 3.2) to follow the high-scoring template: action -> precise behavior/side-effects -> when to use vs. the nearest related tool -> Returns shape. Also add .describe() to previously bare params (set_blend_mode, set_constraints, the create_* shape tools, create_variable) to lift Parameter Semantics. The server score is 60% average + 40% lowest TDQS, so raising the whole sub-4.0 floor cluster is the highest-leverage move. No behavior changes; tool count and schemas are unchanged.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Rewrites the 31 tool descriptions Glama scored ≤ 4.0/5 so they follow the high-scoring template:
action → precise behavior/side-effects → when to use vs. the nearest related tool →
Returnsshape.Also adds
.describe()to previously bare params (set_blend_mode,set_constraints, thecreate_*shape tools,
create_variable) to lift the Parameter Semantics dimension.Why
Glama's server score is 60% average TDQS + 40% lowest TDQS, so lifting the whole sub-4.0 floor
cluster is the highest-leverage move on the current A / 83% rating. The lowest scorers were
rename_page/set_reactions/set_visible(3.2), which dragged the 40% term.Targets the dimensions Glama flagged (Behavioral Transparency, Usage Guidelines, Parameter Semantics).
Deliberately does not touch Tool Count Appropriateness (2/5, structural — not cutting tool breadth
for a score) and leaves > 4.0 tools alone to avoid gold-plating.
Scope / safety
.describe()text only — no behavior changes.ALL_TOOL_SPECS.lengthunaffected).typecheck/lint/format:check/knip/build/test(693 tests).Re-score (post-merge, manual)
Glama won't re-scan automatically: publish a new npm version, then bump the Glama build spec version →
Deploy → Make Release to trigger re-scoring.