Server Quality Checklist

Tool Scores

• get_game_statsA
  4.5/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  No annotations are provided, so the description carries the full burden. It discloses that the tool is a read-only stats getter (safe, non-mutating), and contextualizes the output fields (dictionary size, eligible answers, uncertainty in bits). While it doesn't describe return format details, the description sufficiently conveys the read-only nature and what data it surfaces for a game-state tool with no destructive behavior.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-structured and front-loaded, with the core purpose stated first and usage guidance following. Every sentence adds value. Slightly more verbose than necessary but justified by the important exclusion guidance regarding the sibling tool.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  This is a simple 0-parameter, read-only stats tool with no output schema. The description explains what data it returns (dictionary size, eligible answers, uncertainty), when to use it, and importantly warns against the expensive alternative path. This is functionally complete for its scope.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The tool has 0 parameters. With no parameters to document, the baseline is 4. There is nothing the description needs to add about parameter syntax since none exist.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool gets the state of a Wordle game (guess dictionary size, eligible answer count, starting uncertainty in bits). The verb 'get' plus resource 'game state' is specific and distinct from the sibling recommend_guesses, which focuses on suggesting guesses.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description explicitly says to call this at the START before the first guess, and provides an explicit exclusion: do NOT call recommend_guesses with an empty guess history because scoring the full dictionary is too expensive, so open with a standard high-information first word instead. This clearly delineates when to use this tool vs. the sibling.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• recommend_guessesA
  4.7/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  No annotations are provided, so the description carries the full burden. It discloses the ranking criterion (expected information gain, lower bits = better), distinguishes the two recommendation lists (best_answers vs best_overall) and what each is for, and describes game-state statistics returned including remaining possibilities and uncertainty in bits. It doesn't discuss edge cases (e.g., invalid states, duplicate guesses), but covers the core behavioral contract well for a non-destructive calculation tool.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Each sentence earns its place: the opening states purpose, the second block covers invocation timing and parameter semantics with an example, and the final sentence covers return-value interpretation. No filler or redundancy, well front-loaded with the core action.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with 2 required array parameters, no output schema, and no annotations, the description is complete: it explains both parameters with formats and example, describes the three categories of return data, gives behavioral guidance for selecting among them, and clearly scopes input requirements ('full game so far'). No output schema exists, so describing the returned fields is necessary and done well.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, so the description must compensate fully. It does: it defines words as 'every guessed word' in order, defines feedback format per-character ('g'/'y'/'x' each with explicit meaning), enforces one feedback string per guess, and gives a concrete example mapping words=['crane'] to feedback=['xyxgx']. This substantially exceeds the bare array-of-strings schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool returns 'ranked next-guess recommendations for an in-progress Wordle game' using a specific verb ('Get ranked...recommendations') and resource (next guesses for Wordle). It distinguishes from sibling get_game_stats by focusing on recommendations rather than statistics, and even describes what the returned fields contain.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives explicit when-to-use guidance: 'Call this AFTER each guess, passing the full game so far' and provides concrete format rules for the feedback strings ('g', 'y', 'x'). It also includes a worked example (CRANE = 'xyxgx') and end-state guidance on when to prefer best_answers vs best_overall. This is exceptionally actionable.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.