Server Quality Checklist

Tool Scores

• doctorA
  4.2/5.0
  Behavior4/5

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

  Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false), so the description only needs to add context beyond that. It adds the operational trigger and the specific diagnostic scope, which is meaningful value on top of the structured data. 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?

  Two terse sentences: the first front-loads the purpose and diagnostic scope, the second gives the trigger condition. Zero waste, efficient, and the critical information is placed first.

  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?

  Complete for a diagnostic tool: purpose, scope, and trigger are all stated, the single parameter is fully documented in the schema, and annotations carry the safety profile. Minor omission is that the return/output format isn't characterized, but with no output schema and a simple diagnostic, this is negligible.

  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%, and the single 'deep' parameter is fully documented in the schema, including the ACP handshake sequence and what it adds to output. The description text adds no parameter detail, but the schema already carries the full burden, so the baseline 3 is appropriate.

  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?

  States a specific verb (diagnose) and resource (delegation setup) plus the exact scope of inspection: plugin version, MCP client capabilities, cursor-agent launcher resolution. This clearly distinguishes it from sibling tools delegate and cancel, and the title reinforces it with 'Diagnose Cursor delegation setup'.

  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?

  Gives an explicit trigger condition: 'Run when delegation fails or agent.found is false.' This tells the agent precisely when to invoke the tool. It does not explicitly state when not to use it or name alternatives, but the siblings (delegate, cancel) are semantically distinct operations that don't need exclusion.

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

• cancelA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare destructiveHint=true and idempotentHint=true, so the description's job is to add context beyond that. It does: it discloses the advisory/non-guaranteed nature, notes that a delegate result may still carry cancelRequested, and enumerates the full status space (cancelled, killed, not-running, not-found) including what killed means. No contradiction with the annotations.

  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?

  One focused paragraph that front-loads purpose before the caveat and status enumeration. Every clause carries information — the advisory note, the cancelRequested side effect, and four distinct statuses. It is slightly dense, but nothing is filler.

  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?

  Despite having no output schema, the description effectively documents return semantics by enumerating the four possible statuses and what each means. For a 2-parameter mutating tool, the behavioral guarantees, edge cases (not-running, not-found), and the force parameter are all covered. A minor gap is the lack of guidance on how long the 'short grace period' is for force.

  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 50%: 'force' is well-documented in the schema but 'sessionId' has no description there. The description compensates by naming sessionId as the identifier of the in-flight delegation, giving it purpose. It does not add formatting or provenance detail, but for a string id this is adequate.

  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 pair — 'Best-effort cancel of an in-flight delegation by sessionId' — that names the operation, the target, and the key handle. It also distinguishes itself implicitly from the sibling 'delegate' (which creates the delegation that this tool cancels), so an agent can separate the two without opening schemas.

  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 conveys when to use it (to cancel an in-flight delegation) and sets expectations up front with 'best-effort' and 'advisory'. The status list tells the caller what outcomes to anticipate. It does not explicitly name when-not-to-use or recommend an alternative, but against the sibling set (delegate creates, doctor diagnoses) the boundary is clear enough.

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

• delegateA
  4.9/5.0
  Behavior5/5

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

  Directly discloses the behavior that makes destructiveHint and openWorldHint true: 'Auto-approves every permission the agent requests, in any mode and anywhere on disk.' It also reveals the clarification interaction pattern (prose in result, resume with resumeSessionId) and that invalid values fail before the prompt while naming the accepted set. This adds genuine context far beyond the bare annotations and does not contradict them.

  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?

  Six sentences, each pulling weight: purpose, prohibition, safety warning, interaction contract, defaults policy, skill pointer. The most critical warning (auto-approve anywhere on disk) is front-loaded in the third sentence, not buried. No filler, no restatement of schema content.

  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 9-parameter, 2-required, destructive, open-world tool with no output schema, this is remarkably complete. It covers safety, interaction protocol, defaults policy, per-parameter touch rules, and even the resolution of paths (relative paths resolve against workspace but are not limited to it) and error behavior (invalid effort values fail before the prompt, skips surface in protocolWarnings). Nothing an agent needs to call it correctly is missing.

  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%, so the baseline is 3. The description earns a 4 by adding a cross-cutting policy the schema alone can't express — the 'touch nothing unless the user asks' rule that applies across fast, model, effort, and context — and by signaling which params are safe to pass only on explicit request. It doesn't need to restate field meanings since the schema already documents them fully.

  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?

  Opens with a specific verb+resource: 'Delegate a coding task to cursor-agent over ACP.' It goes further and distinguishes itself from the naive alternative with 'Never shell out to cursor-agent — use this tool only,' so the agent cannot mistake its scope. Unambiguous.

  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?

  Explicit when-to-use and when-not-to-use guidance: the prohibition on shelling out, the warning that it auto-approves every permission in any mode and anywhere on disk, and a clear defaults policy — 'Keep model, fast and effort at their defaults unless the user explicitly asks.' Multiple params get a 'only when the user asks' qualifier, which is exactly the guardrail an agent needs for a destructive, open-world tool.

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