Server Quality Checklist

Tool Scores

• compressA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the responsibility of behavioral disclosure. It explains that the result is a compact extract with a footer ref, that the full output remains retrievable via that ref, and how to use the sibling tool to retrieve it. This goes beyond a simple one-liner and gives the agent a clear mental model of the tool's side effects.

  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?

  The description is two sentences: the first establishes purpose and the second explains the return format and retrieval path. It is front-loaded with the key action, contains no filler, and every clause earns its place. Perfectly sized for a tool of this complexity.

  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?

  Given three parameters, no output schema, and one sibling tool, the description adequately explains what the tool returns ('a compact extract'), how to access the full output (via ref in footer), and how that connects to expand_tool_output. It does not mention edge cases or validation rules, but for a straightforward compression tool it is sufficiently complete.

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

  Parameters3/5

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

  Schema description coverage is 100%, so each parameter is described in the schema. The description itself adds little new meaning: it reiterates 'optional query' and 'token budget' but does not provide additional context beyond what the schema already specifies. Baseline 3 is appropriate given the high schema coverage.

  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 verb ('Compress'), the resource ('a bloated tool output or long text'), and the specific goal ('fits a token budget while keeping what's relevant'). It also distinguishes from the sibling tool by explaining the ref mechanism and pointing to expand_tool_output for retrieval.

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

  Usage Guidelines4/5

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

  The description gives clear context for use (when output is bloated or needs to fit a token budget) and references expand_tool_output as the complementary tool for reading the full output. It lacks explicit exclusions or 'when not to use' but covers the primary usage scenario well.

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

• expand_tool_outputA
  4.7/5.0
  Behavior4/5

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

  With no annotations available, the description carries the full burden. It discloses the pagination behavior (returns a page of characters, start/length for more), the nature of the output (full, uncompressed tool output), and the dependency on a ref. It does not explicitly state side effects, but 'Retrieve' strongly implies a read-only operation. It lacks edge-case details like invalid ref behavior, but for a simple retrieval tool this is sufficient.

  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?

  The description is three sentences with zero filler. The first sentence states the primary action, the second provides usage context and importance, and the third explains paging. It is front-loaded with the core purpose and every sentence earns its place.

  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 no output schema, the description adequately covers the return value by stating it returns the 'full, uncompressed tool output' and is paginated as 'a page of characters.' It also addresses why this tool matters (omitted fields in compressed results) and how to retrieve all data. The examples of missing fields provide practical context, making the tool's purpose and usage fully understandable.

  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 coverage is 100% with clear descriptions for all three parameters. The description adds value by explaining the relationship between start and length ('use start/length to page through more'), which synthesizes the parameters into a usage pattern. It also clarifies the ref's origin (shown in the compressed result's footer), which is not in the schema. This meaningfully supplements the 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 opens with a specific verb+resource: 'Retrieve the full, uncompressed tool output behind a tooltrim reference.' It clearly distinguishes itself from the sibling compress by focusing on decompression/retrieval. The reference format (ref=XXXX) is explicitly explained, leaving no ambiguity about what the tool does.

  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 provides explicit when-to-use guidance: 'before you answer the user or take an action that depends on a compressed result, if any detail you need is not clearly present in it, call this tool with that ref.' It also explains the contextual trigger (compressed observation may have omitted fields) and gives concrete examples of missing data (ids, amounts, list items, statuses). While it doesn't mention the sibling tool by name, the usage context is unambiguous.

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