Server Quality Checklist

Tool Scores

• cancel_requestA
  3.6/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of transparency. It only notes the operation works on pending requests and 'releases human agents,' but does not disclose whether the cancellation is reversible, what state changes occur, or if errors arise for non-pending requests. This is insufficient for a mutation tool.

  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 concise, two sentences, and front-loaded with purpose. However, the typo 'cQnce' is a minor distraction and reduces polish.

  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?

  For a simple single-parameter tool, the description is adequate but not complete. It lacks details on response behavior, edge cases, or potential failures, which an agent would need for reliable invocation.

  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?

  The input schema fully documents the only parameter (requestId) with a description. The tool description adds no parameter information, but since schema coverage is 100%, the baseline of 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?

  The description clearly states the tool cancels a pending authorization request, using a specific verb and resource. It is distinguishable from siblings like submit_authorization_request and poll_request_status, which have different actions.

  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 explicit usage context: 'Use this if the action is no longer needed and you want to release the human agents.' This tells the agent when to invoke the tool, though it lacks explicit exclusions or alternative comparisons.

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

• get_requestA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It describes the return payload but does not explicitly confirm read-only behavior, error handling, or permissions. The verb 'Get' implies a safe read, but this is not spelled out.

  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 sentence that front-loads the purpose and includes useful detail about what is returned. Every word adds value with no redundancy or fluff.

  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 simple read tool with one parameter and no output schema, the description adequately explains the return content. It lacks explicit alternatives, but the level of detail is sufficient for an agent to understand the tool's role.

  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?

  The single parameter requestId is fully described in the schema (100% coverage), so the description adds no additional parameter semantics. The baseline is 3 because the schema already carries the meaning.

  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 a specific verb and resource: 'Get full details of a single authorization request.' It enumerates the content (payload, metadata, agent responses, current status) and distinguishes itself from siblings like poll_request_status (which likely only returns status) and list_requests (which lists multiple).

  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 implies usage when full details of a single request are needed, but it does not explicitly contrast with alternatives or provide when-not-to-use guidance. Sibling names are known, but the description itself lacks explicit usage context.

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

• list_requestsA
  4/5.0
  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. 'List' implies a read-only operation, but the description does not explicitly state that it is non-mutating, nor does it mention pagination behavior or default limits. It adds minimal behavioral context beyond the schema.

  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 long and front-loaded with the primary action ('List authorization requests'), followed by concise use cases. Every word earns its place; there is no redundancy or fluff.

  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?

  The description covers the tool's purpose and typical use cases, which is adequate for a list operation. However, with 7 parameters and no output schema, it does not mention that results can be filtered or paginated, nor the shape of the return value. The schema compensates for filter details, but the description could be slightly richer about the response structure.

  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 baseline is 3. The description does not mention any parameters or add meaning beyond what the schema already provides for tags, status, date filters, or pagination. It neither clarifies nor repeats parameter details.

  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 'List authorization requests for this project,' which is a specific verb (list), resource (authorization requests), and scope (this project). This clearly distinguishes it from siblings like get_request (single request) and cancel_request (mutation).

  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 provides clear usage context: 'Useful for monitoring ongoing requests, debugging workflows, and auditing decisions.' However, it does not explicitly exclude alternatives like get_request for individual requests or poll_request_status for status checks, so it lacks explicit when-not guidance.

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

• wait_for_approvalA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden and does well: it discloses blocking behavior, timeout behavior, and possible statuses (APPROVED, REJECTED, EXPIRED). It does not mention error handling or return format, but the core behavioral traits are clearly communicated.

  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, front-loaded with the critical blocking behavior, and zero filler. Every clause adds value, and the instruction about not proceeding on non-approval is clear and action-oriented.

  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 tool has no output schema, so the description should explain what the result contains. It names the statuses but not the overall response structure (e.g., whether it's an object with a status field). For a blocking HITL tool, this is a moderate gap; the complexity of routing options is left entirely to the schema.

  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 coverage is 100%, so the schema already describes all 7 parameters. The description adds no additional parameter-specific meaning beyond implying the tool blocks and returns a status. Baseline 3 is appropriate; it neither degrades nor enhances schema 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 the tool's function: 'Submit an authorization request and BLOCK until a human approves or rejects it (or until the timeout elapses).' It uses specific verbs (submit, block) and identifies the resource (authorization request), distinguishing it from siblings like submit_authorization_request which likely does not block.

  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 positions this as 'the primary tool for human-in-the-loop workflows' and provides clear post-conditions: 'proceed ONLY if status is APPROVED' and 'do NOT proceed' on REJECTED or EXPIRED. It lacks explicit alternatives/exclusions, but the guidance on when to use it is strong.

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

• poll_request_statusA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the behavioral disclosure burden. It explains the meaning of terminal statuses (APPROVED, REJECTED, EXPIRED, CANCELLED) and PENDING, and clarifies that this is a non-blocking operation by directing blocking waits elsewhere. While it doesn't cover error behavior or rate limits, the key behavior is transparent.

  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, with the core action front-loaded in the first sentence, followed by status definitions and an alternative tool reference. Every sentence contributes value and there is no waste.

  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 simple one-parameter read-only tool, the description is largely complete. It covers the statuses and the alternative, and the lack of an output schema is partially compensated by listing expected status values. It could explicitly state the return format or error handling, but this is a minor gap for such a simple tool.

  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?

  The schema covers the single parameter fully with a description for requestId, so the schema carries the parameter semantics. The tool description does not add extra detail about the parameter, but the baseline is 3 given 100% schema coverage.

  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 uses a specific verb 'Check' and identifies the resource as the status of a cQnce authorization request. It also lists terminal statuses, making the tool's function unmistakable. The explicit mention of wait_for_approval as an alternative further clarifies its distinct role.

  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 states when to use this tool versus wait_for_approval, saying 'For a blocking wait, use wait_for_approval instead.' This provides clear guidance for the primary alternative. It does not mention other siblings like get_request, but the core usage distinction is well covered.

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

• submit_authorization_requestA
  4.2/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. It discloses the key behavior (returns requestId) and its intended pre-action role. However, it doesn't mention error scenarios, idempotency, or side effects like human notifications.

  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, front-loaded with the primary verb and resource, then concise usage and next-step guidance. No 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?

  No output schema, but description explains the key return (requestId) and how to use it with sibling tools. Covers the tool's workflow well, though it could mention response details or failure modes for fuller completeness.

  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 schema already documents all six parameters. Description adds no parameter-level detail beyond schema, which is acceptable given the high coverage.

  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 'Submit a human authorization request' – specific verb+resource. Distinguishes from siblings by noting it's for risky/destructive actions and returns a requestId used with wait_for_approval or poll_request_status.

  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 says 'Use this BEFORE performing any risky, destructive, or irreversible action' with concrete examples. Mentions follow-up tools (wait_for_approval, poll_request_status) but does not explicitly contrast with other siblings like get_request or cancel_request.

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