Server Quality Checklist

Tool Scores

• delegate_taskB
  3.3/5.0
  Behavior3/5

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

  With no annotations provided, the description must carry the full burden of behavioral disclosure. It does disclose that the task is asynchronous and that the return value is limited to task and conversation handles, which is useful. However, it does not explain side effects, required permissions, persistence, or how the task will eventually be tracked, leaving significant behavioral context undisclosed.

  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, front-loaded sentence with no filler or redundant information. It efficiently communicates the core action and a key behavioral trait (asynchronous) plus return-value limitation. Every clause earns its place, making it appropriately concise for the content it delivers.

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

  Completeness2/5

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

  The tool has no output schema and only a sparse description, yet it has three parameters (two required) and sits in a lifecycle with siblings. The description is not complete enough to guide the agent: it does not explain the meaning of the parameters, the structure of the handles it returns, or how this task relates to subsequent tools like get_task or continue_task. Given the moderate complexity and absence of annotations/output schema, more detail is needed.

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

  Parameters1/5

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

  The schema has 0% description coverage, meaning the description must compensate for explaining parameters like prompt, workspace, and allowed_paths. The description provides no parameter-specific semantics—it does not define what 'prompt' should contain, what 'workspace' refers to, or what 'allowed_paths' controls. This leaves the agent without essential guidance for filling in the parameters correctly.

  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 action: 'Create an asynchronous secure coding task.' It uses a specific verb ('Create') and resource ('secure coding task'), and distinguishes itself from sibling tools like get_task and continue_task by focusing on new task creation. The mention of returning 'only its task and conversation handles' further clarifies its unique scope.

  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 the tool is for creating new asynchronous tasks, which suggests when to use it (when you need to delegate a new task). However, it provides no explicit guidance on when not to use it or how it compares to alternatives like continue_task. There are no named alternatives or exclusion criteria, so the usage context is only implied.

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

• get_diffB
  3.3/5.0
  Behavior3/5

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

  With no annotations, the description must disclose behavior. It adds useful context by stating the record is 'small' and excludes full source and tool logs, setting expectations for response size and content. However, it does not describe return format, error handling, or explicitly confirm read-only behavior. This is partial disclosure, not comprehensive.

  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 concise sentences, front-loaded with the core purpose ('Get a small audited change record') and followed by a clarifying exclusion. Every word earns its place; there is no redundancy or irrelevant information.

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

  Completeness2/5

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

  For a tool with no output schema and 0% parameter coverage, the description is incomplete. It neither explains what the returned record contains nor how the parameters combine (e.g., Is path required for file diffs? What if only task_id is given?). The exclusions help but leave significant gaps for an agent to invoke correctly.

  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?

  Schema description coverage is 0%, so the description must compensate. It mentions 'task or file', which hints at the two parameters (task_id and path), but does not clarify their relationship, whether path is optional, or how they interact. The schema indicates task_id is required, but the description does not reinforce this or explain file path usage.

  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 identifies the tool's purpose: retrieving a 'small audited change record' for a task or file. The verb 'Get' and specific resource ('change record') distinguish it from siblings like get_task, which likely retrieves task details. The exclusion clause ('Full source and tool logs are excluded') further narrows the scope.

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

  Usage Guidelines2/5

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

  No guidance is given on when to use this tool versus alternatives. The description does not mention conditions, prerequisites, or contrasts with sibling tools (e.g., get_task for task details). It simply states what it does without context for selection.

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

• continue_taskA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description must carry the transparency burden. It reveals that the tool resumes a task using its persisted conversation, which is a useful behavioral trait beyond just 'resume'. However, it does not disclose potential side effects, such as state changes or whether the operation is idempotent, leaving some uncertainty.

  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, front-loaded sentence of 10 words with no filler. Every word contributes to the core meaning, making it exceptionally concise and well-structured.

  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?

  Given the tool's simplicity (2 params, no output schema, no annotations), the description covers the core purpose and mechanism but leaves gaps around the 'prompt' parameter and any caveats about resuming. It is adequate but not fully complete for an agent to confidently invoke it in all scenarios.

  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?

  Schema description coverage is 0%, so the description is expected to compensate. It does not mention the 'prompt' parameter at all, and while 'task_id' is implied by the word 'task', the description adds no semantic detail about either parameter beyond what the schema provides.

  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 'Resume' and identifies the resource as 'a paused or failed task', which clearly distinguishes it from sibling tools like get_task, cancel_task, and delegate_task. The mechanism 'using its persisted conversation' further clarifies its unique 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 provides a clear context for when to use the tool: when a task is paused or failed. It does not explicitly mention alternatives or exclusions, but the condition 'paused or failed' is a strong usage indicator, and the sibling tools are contextually distinct.

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

• cancel_taskA
  3.9/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states that a cancelled task 'can no longer be resumed', disclosing irreversibility—a key behavioral trait for a cancellation operation. It does not cover other aspects like idempotency or permissions, but the primary consequence is clearly conveyed.

  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 short sentences, front-loaded with the verb 'Cancel', and every word earns its place. It conveys both the action and the critical consequence without any 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 cancellation tool with a single parameter and no output schema, the description covers the essential context: the action and irreversibility. It could mention return values or idle cases, but given the simplicity, it is reasonably complete and clearly distinguishes from continue_task.

  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 description does not mention the task_id parameter at all, and schema description coverage is 0%, so the parameter semantics rest entirely on the property name. While task_id is self-explanatory and the schema specifies UUID format, the description fails to compensate for the low 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 states 'Cancel a task' with a specific verb and resource, clearly distinguishing this from sibling tools like get_task, continue_task, and delegate_task. The added clarification 'It can no longer be resumed' reinforces the terminal nature of the operation.

  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?

  Usage context is only implied: the description suggests this is the tool to use when a task must be terminated and cannot be continued later, which contrasts with continue_task. However, there is no explicit guidance on when to use this tool versus alternatives or whether there are prerequisites.

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

• get_taskA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses a key behavioral trait: the result is compact and excludes model transcripts and tool logs. This helps set expectations about the output's scope. It doesn't mention errors or auth, but for a simple get operation, the disclosure is sufficient.

  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 concise sentence that front-loads the primary action ('Get a compact task receipt') and adds a useful qualifier about what is excluded. Every word earns its place; no wasted text.

  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 tool with one parameter and no output schema, the description is largely complete. It clarifies the purpose and a key limitation. It might benefit from a brief note about what a 'task receipt' includes, but the current phrasing is sufficient for most use cases.

  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 input schema has one parameter (task_id) with format uuid, but the description mentions no parameter details. Schema description coverage is 0%, so the description should compensate, but it doesn't add any meaning to the parameter. While the parameter is self-explanatory, the description offers no semantic enhancement beyond the schema.

  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: 'Get a compact task receipt.' It uses a specific verb ('Get') and resource ('task receipt'), and distinguishes itself from sibling tools like continue_task and get_diff by clarifying it returns a receipt rather than transcripts or logs.

  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 context for use: it returns a compact receipt and explicitly notes what it does not include (model transcripts or tool logs). While it doesn't name alternative tools, this implies it should be used when a concise summary is needed, not when detailed logs are required.

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