Server Quality Checklist

Tool Scores

• submit_candidate_decisionA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It reveals that submissions are stored as uncurated candidates requiring human approval before becoming canonical, and nothing is auto-promoted. However, it does not mention idempotency or potential side effects like duplicates, which slightly limits transparency.

  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 moderately sized and front-loaded with the main purpose. It uses a clear structure with a brief overview followed by detailed usage guidance. While mostly concise, a slightly more compact version could be achieved without losing clarity.

  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 that an output schema exists (as indicated by context), the description appropriately notes that the tool returns the new candidate decision's id. The description, combined with the schema, provides sufficient context for the agent to understand the tool's functionality and lifecycle.

  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 the input schema already fully documents each parameter. The description does not add new meaning beyond reiterating the tool's purpose. A baseline score of 3 is appropriate since the schema does the heavy lifting.

  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 records a new engineering convention for human review. It distinguishes itself from siblings like 'get_decisions_for_context' (reading) and 'submit_feedback' (feedback) by focusing on submitting a candidate convention for later approval.

  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 explains when to call the tool: 'when you find an undocumented convention, a tricky gotcha, or a preferred pattern that Metatron did not already know but future agents should.' It also clarifies that submissions are not auto-promoted, providing clear context for appropriate use.

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

• submit_feedbackA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses behavior: ratings affect a time-decayed helpfulness signal, unknown indices and out-of-range scores are dropped, what_was_missing is stored as a gap for human curation, and the tool does not directly promote/demote decisions. It also describes the return value.

  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 with clear paragraphs covering purpose, usage, behavior, and return. It front-loads the main action. Every sentence adds value, though the description is somewhat lengthy; it could be slightly more concise but remains effective.

  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 tool's complexity (6 parameters, no required) and the presence of an output schema, the description covers all aspects: purpose, when to use, parameter behavior, what happens internally, and the return value. It provides sufficient context for an agent to use the tool correctly.

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

  Parameters5/5

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

  Schema description coverage is 100%, providing a baseline of 3. The description adds significant meaning: it explains that ratings are 1-based indices with scores 1-10, clarifies that helpful/unhelpful are optional shorthands, and describes how what_was_missing is used. This goes well beyond the schema's descriptions.

  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: 'Report how helpful the served decisions were, and what was missing.' It specifies the action (submit feedback), the resource (decisions from get_decisions_for_context), and distinguishes from siblings by focusing on feedback rather than fetching decisions (get_decisions_for_context) or proposing new ones (submit_candidate_decision).

  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 when to call: 'Call this after a task where you used Metatron's decisions.' It provides context (reference the query_id) and explains what to provide. While it doesn't explicitly state when not to use, it implicitly excludes use cases not involving feedback on served decisions.

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

• get_decisions_for_contextA
  4.8/5.0
  Behavior5/5

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

  No annotations provided, so description fully carries the burden. It discloses that only human-approved decisions are returned, ranked by scope match and past ratings, that each call records a usage event for feedback linkage, and details the exact return format including the query token and the case of no matches.

  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 moderately long but well-structured: opening purpose, usage guidance, behavioral details, return format, and reminder. It is front-loaded with critical information, and every sentence adds value. Could be slightly more concise but overall effective.

  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?

  The description fully explains the tool's behavior, return format (including header, numbered decisions, and no-match case), and how to use the output with siblings. Despite the presence of an output schema (not shown here), the description covers all necessary context for correct invocation.

  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 100%, so baseline is 3. The description adds value by giving concrete examples for 'file_path_or_area' ('src/routes/api/users.py' or 'billing') and for 'task_description', and by explaining how these parameters fit into the workflow (e.g., 'surfaces ... conventions for that part of the codebase').

  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 fetches 'team's canonical engineering decisions' for a file/area and task, using a specific verb 'fetch' and resource. It distinguishes from sibling tools 'submit_candidate_decision' and 'submit_feedback' by focusing on retrieval, not submission or feedback.

  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 instructs to 'Call this FIRST, before writing or editing code in an area — and again when you move to a new file or module.' It also tells agents to use 'submit_feedback' afterward, providing clear context and alternatives.

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