Server Quality Checklist

Tool Scores

• distil_savingsA
  4.5/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint: true, destructiveHint: false, and idempotentHint: true. The description adds that it takes no arguments and that an empty ledger reports zeros, which is transparent. There is no contradiction with annotations.

  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, front-loaded with the result format and purpose. Every sentence adds value without redundancy, achieving high conciseness.

  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?

  Given no parameters, no output schema, and annotations covering safety, the description completely explains the return format, scope (all requests on machine), and what it does not tell (correctness). It is fully adequate for the tool.

  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?

  With zero parameters, the baseline is 4. The description correctly states 'Takes no arguments', which is clear and sufficient for the parameter semantics dimension.

  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 it reports cumulative savings from the distil ledger with specific fields (runs, tokens_saved, dollars_saved). It distinguishes from sibling tools by clarifying it says nothing about compression correctness, which differentiates it from distil_compress and distil_expand.

  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 explicitly says to use it to answer 'how much has distil saved me' and notes it covers all requests on the machine, not just the session. It does not explicitly state when not to use it or mention alternative tools, but the context is clear enough.

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

• distil_compressA
  4.8/5.0
  Behavior5/5

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

  The description discloses key behavioral traits beyond the annotations: local encrypted storage, owner-only access, never sent elsewhere, error return format ('error: ...' with isError), and the condition for handle=null. This significantly aids the agent in understanding side effects and error handling.

  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 a single paragraph that efficiently covers purpose, output, usage, and behavior. It is front-loaded with the main purpose and each sentence provides necessary information, though it is slightly dense. No wasted words, but could be broken into bullet points for clarity.

  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?

  Given the simple single-parameter tool with no output schema, the description is remarkably complete. It explains the return value structure, handle behavior, storage details, token savings, error handling, and usage conditions. The annotations already cover safety and idempotency, so the description fills all remaining contextual gaps.

  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?

  With 100% schema coverage, the baseline is 3. The description adds value by emphasizing that the text must be passed verbatim without pre-summarization or truncation, which is critical for lossless recovery. This extra guidance justifies a higher score.

  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's purpose: 'Reversibly compress a text blob' to keep large tool output in context cheaply. It distinguishes itself from siblings by mentioning how the handle can recover the original via distil_expand, and implicitly differentiates from distil_savings by focusing on compression.

  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?

  Explicitly states when to use: 'when a tool result is large enough that carrying it verbatim is wasteful' and when not: 'skip it for short text'. Also explains the behavior for short text, providing clear decision guidance without alternative tools.

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

• distil_expandA
  4.9/5.0
  Behavior5/5

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

  Annotations already provide readOnlyHint, idempotentHint, destructiveHint. Description adds vital context: local encrypted store, cross-session but not cross-machine, TTL-based eviction, and specific error message format with isError flag. No contradiction.

  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?

  Well-structured, front-loaded with primary action, each sentence serves a purpose. No fluff, covers all necessary aspects efficiently.

  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?

  Given single parameter, rich annotations, and no output schema, the description is complete: explains purpose, usage, behavior, error handling, and constraints. No gaps.

  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 has 100% coverage with pattern and description. Description adds value by clarifying the handle is content-addressed and stable across runs, and that any other shape is rejected. Minor but helpful.

  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 explicitly states the tool recovers original text from an 8-hex handle, distinguishing it from its sibling distil_compress. It is specific and clear.

  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?

  Explicitly advises when to use (when digest lacks detail) and when not to use (prefer reading digest first), plus error handling guidance ('re-run original tool, not retry').

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