Server Quality Checklist

Tool Scores

• load_planA
  3.5/5.0
  Behavior3/5

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

  Annotations declare non-destructive and non-open-world, so the description only needs to add context. It adds that this is a load step in a security-review workflow, but doesn't explain side effects, what happens to the loaded plan, or validation behavior. That is a modest addition, not a rich one.

  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?

  One sentence, front-loaded with the action and resource. No wasted 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?

  With one parameter, no output schema, and simple annotations, the description covers the basics but misses details like expected return, behavior on invalid paths, and the exact meaning of 'load.' For an agent to invoke this correctly, the path semantics and outcome should be clearer.

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

  Parameters2/5

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

  The schema has 0% description coverage for the single 'path' parameter, so the description must compensate. It only refers to the plan as 'supplied,' implying the path is the plan location, but doesn't clarify path type, format, or how the plan is consumed. This leaves an agent guessing about a required parameter.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  States a specific verb ('Load') and resource ('security-review plan'), with a usage context ('before execution'). It clearly differs from siblings like get_task and status, though it doesn't name them. Slight ambiguity remains in what 'load' means operationally.

  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?

  Provides a clear usage context: 'before execution' signals when to call this tool. It does not explicitly exclude alternatives or name siblings, but for a simple plan-loading step this is sufficient.

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

• report_doneA
  4.4/5.0
  Behavior4/5

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

  The description discloses meaningful behavior beyond the annotations: it mechanically verifies source coverage, returns the exact missing read when incomplete, and enforces content constraints per outcome. This is especially valuable because annotations only indicate non-destructiveness and closed-world behavior, not the verification workflow.

  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 dense but every sentence earns its place: purpose, validation behavior, per-outcome payload rules, and next-step workflow. It is front-loaded with the core action and avoids 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?

  For a structured submission tool with no output schema, the description provides strong workflow context and error behavior. It could be more complete by explaining what an 'accepted result' looks like and clarifying step_id/summary expectations, but overall it gives enough for an agent to operate correctly.

  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?

  With 0% schema description coverage, the description partially compensates by explaining outcome-specific requirements for finding_ids, evidence, and artifacts, and by describing evidence as concise source ranges. However, it leaves step_id, summary, and the evidence note field semantically unexplained, so the compensation is incomplete.

  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 and resource: 'Submit the structured result.' It goes on to explain that the tool verifies source coverage and reports missing reads, making its role clear. It also distinguishes itself from siblings by locating it in the workflow between get_task and status.

  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 concrete when-to-use guidance: submit results, then call get_task until COMPLETE, then call status for final totals. It also gives outcome-specific formatting rules for NO FINDINGS versus FINDING/CORROBORATION, leaving little ambiguity about when and how to invoke the tool.

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

• statusA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: the tool is authoritative for final totals, and its diagnostics should be exclusively trusted after COMPLETE. 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 sentences, no wasted words. The core purpose and read-only nature are front-loaded, followed by the critical usage instruction. Every phrase contributes meaning.

  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?

  For a parameterless status tool, the description covers what it does, when to call it, and how to use its output for final totals. It does not describe the structure of diagnostics, but the authoritative usage guidance compensates enough given the simple interface and no output schema.

  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?

  The tool has zero parameters and the schema is fully descriptive with an empty object, so there is no parameter burden for the description to carry. The description even models the intended call as 'status {}', which is helpful. Baseline for 0 params is 4; no additional explanation is 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?

  Description states a specific verb ('Return') and resource ('read-only authoritative review progress and diagnostics'), clearly distinguishing it as the source of final totals. The phrase 'authoritative' positions it against siblings like get_task without ambiguity. It is immediately obvious what this 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 Guidelines4/5

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

  Explicitly states when to call it: 'After the server reports COMPLETE, call status {}'. This gives clear timing context and tells the agent to use its diagnostics for final totals. It does not explicitly name alternatives or when not to use it, so it falls short of a 5.

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

• get_taskA
  4.9/5.0
  Behavior5/5

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

  Beyond the annotations (openWorldHint=false, destructiveHint=false), the description reveals non-obvious behavior: get_task can be re-invoked to repeat the current task, its response carries an execution_instruction, and the agent is expected to loop back. This meaningfully helps the agent predict and act on the tool's behavior.

  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 a single dense sentence that front-loads the core purpose and then packs the necessary behavioral workflow into the rest. Every clause adds information; there is no filler or restatement.

  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 zero-parameter tool with no output schema, the description is sufficient: it says what the tool does, what the agent should do with the returned task, and what to call next. The absence of detailed return-field documentation is acceptable because the execution_instruction is explicitly referenced.

  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?

  The tool has zero parameters and the schema fully covers this, so no parameter detail is needed. The description also reinforces the expected call shape by literally showing 'get_task {} again,' which is a small but useful confirmation.

  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 states a clear verb-resource pair: it issues or repeats 'the one current security-review task.' It also distinguishes itself from sibling tools by framing get_task as the source of the task and the loop entry point, with report_done as follow-up.

  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 the workflow: read source serially, submit report_done for coverage verification, then immediately call get_task {} again. This gives the agent concrete when-to-use-next guidance and names the sibling tool involved, leaving little to inference.

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