Server Quality Checklist

Tool Scores

• clonst_pingA
  3.9/5.0
  Behavior3/5

  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 consumes no LLM quota and lists the diagnostic checks, but does not specify if there are side effects or network calls.

  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?

  Two sentences: first efficiently lists the diagnostics, second adds the notable quota information. No unnecessary words.

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

  Completeness3/5

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

  The description explains what the tool checks but not what it returns (e.g., health status format). Given no output schema, more detail on the response would improve completeness.

  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?

  There are no parameters, so the baseline is 4. The description adds value by explaining the tool's purpose, which is sufficient given no parameters are needed.

  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 'Full Clonst server diagnostic' and lists specific aspects it checks (health, codex CLI availability and version, login status, loaded config, logs directory), distinguishing it from siblings that are summary/review tools.

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

  Usage Guidelines3/5

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

  The description mentions 'Consumes no LLM quota' implying it's safe to use freely, but lacks explicit guidance on when to use this tool instead of siblings like clonst_report_summary or clonst_review.

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

• clonst_reviewA
  4.8/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses behavior: it explains the review round loop, session memory via thread_id, the 50-round cap, the need for critical evaluation, and the next_action field. It also warns about subscription quota and token consumption when using project_path, making agent behavior highly predictable.

  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 dense and informative but lacks structural breaks like bullet points or sections, which would improve scannability. However, every sentence serves a purpose and there is no extraneous information given the tool's complexity.

  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 (10 parameters, iterative process, output schema exists), the description is fully complete. It covers the review workflow, usage conditions, parameter roles, loop mechanism, and safety caps. The presence of an output schema removes the need to describe return values, and the description adequately fills all other 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?

  Although schema description coverage is 100% with parameter descriptions, the tool description adds workflow context beyond schemas. For example, it explains when to pass thread_id (later rounds), why context is ignored if thread_id exists, and that max_rounds should be the same each round. This enriches agent understanding beyond the schema alone.

  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: 'Have a plan, code or proposal critiqued by Codex.' It specifies it provides a structured critique with verdict, changes, and risks. It differentiates from siblings (e.g., clonst_ping, clonst_report_summary) through its detailed description of the review process and iteration loop.

  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 details when to use the tool: 'WHEN TO USE IT: the criterion is LOGIC, not size. Call it by default... for any development that touches the project's logic or behavior.' It also lists exclusions: 'Do NOT use it for pure presentation, documentation, renames without behavior change, or throwaway content.' This provides clear guidance on when to use versus alternatives.

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

• clonst_report_summaryA
  5/5.0
  Behavior5/5

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

  With no annotations provided, the description fully discloses traits: it is idempotent (overwrites on re-call), metadata-only, and does not spawn reviewers or consume LLM quota. No contradictions.

  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?

  Three sentences, each necessary and front-loaded. First sentence states purpose, second gives usage constraints, third adds behavioral traits. No redundant information.

  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 simple schema (2 required params, no enums, no nested objects) and presence of output schema, the description fully covers purpose, when to use, parameter nuances, and behavior. No gaps identified.

  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 coverage is 100% with descriptions, but the description adds critical context: for 'report_id', it distinguishes from 'thread_id'; for 'summary', it specifies 'exact text you gave the user verbatim'. This extra guidance enhances parameter understanding.

  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 seals a plain-language summary into a structured report file. It uses a specific verb ('seal') and resource ('structured review report file'), and distinguishes itself from sibling tools ('clonst_ping', 'clonst_review') by specifying it is called after consensus to store the final summary.

  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 once after a consensus, and clarifies that 'report_id' is from clonst_review (not thread_id). Also mentions metadata-only nature (no reviewer spawn, no LLM quota), providing clear usage context.

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