Server Quality Checklist

Tool Scores

• agent_sendA
  3.7/5.0
  Behavior2/5

  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 only states the basic action and that the recipient receives it in-session. It omits critical traits like delivery guarantees, error handling, or whether the recipient must be online.

  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, front-loaded with the verb and resource, and contains no unnecessary words. Every part adds value.

  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 a simple 3-parameter tool with no output schema or annotations, the description covers the core action but lacks behavioral details that would help an agent use it reliably. It is minimally adequate but has clear gaps.

  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 baseline is 3. The description adds little beyond the schema: it mentions 'by name' for the name parameter but does not provide additional context or constraints for parameters like 'from'.

  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 ('Send') and a clear resource ('message to another agent'). It distinguishes itself from siblings like agent_list or task_create by focusing on inter-agent communication.

  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 clearly states it is for inter-agent comms by name, which implicitly defines when to use it. It does not provide explicit when-not or alternatives, but sibling tools cover different domains, so context is adequate.

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

• task_createA
  3.9/5.0
  Behavior3/5

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

  With no annotations, the description must disclose behavioral traits. It mentions the return format (e.g., DIVE-N) but omits details like side effects, idempotency, authentication requirements, or error handling. Adequate but 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?

  Two concise sentences that front-load the primary action and return value, with no redundant information. Every sentence serves a purpose.

  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 creation tool with 6 optional parameters and no output schema, the description covers the return value but lacks information on error scenarios, rate limits, or behavioral nuances. It is minimally adequate but incomplete.

  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 all parameters (100% coverage), so the description doesn't need to add much. It does add the return id format, which is helpful. Baseline 3 is appropriate as the schema already documents parameter meanings.

  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 action ('Create a task'), specifies the resource ('shared 5dive task queue'), and indicates the return value (id). It distinguishes itself from sibling tools by being the only creation tool among them.

  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 advises 'Use for filing work for an agent or human on the fleet,' providing a clear use case. However, it does not explicitly state when not to use this tool or suggest alternatives, missing an opportunity for fuller guidance.

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

• digest_getA
  4.2/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It implies a read-only operation without stating auth needs or rate limits. Adequate for a simple get tool, but not detailed.

  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, zero waste. Front-loaded with action and resource, followed by parameter guidance. Every sentence earns its place.

  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?

  Given low complexity (1 param, no output schema), description covers purpose and key usage. Could mention default window or return format, but not essential.

  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% with a single enum parameter. Description adds value by suggesting the weekly use case ('Pass window=7d'), beyond the schema's enum listing.

  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 verb 'Get', the resource 'fleet's daily standup digest', and specifies contents (activity, token burn, health). It distinguishes from sibling tools like agent_list or task_create.

  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 hint for parameter window ('Pass window=7d for the weekly view'), but lacks when-not or alternative tool comparisons. Context is clear enough for selection.

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

• agent_listA
  4.3/5.0
  Behavior3/5

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

  No annotations provided, so the description carries full burden. It implies a read-only operation but does not disclose potential behavioral traits like rate limits, pagination, or required permissions. However, for a simple list, this is acceptable.

  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 main action ('List every agent on the box') and lists the fields returned. No wasted words.

  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 simple tool with no parameters and no output schema, the description adequately specifies what the tool does and what fields are returned. It is complete enough for an agent to use correctly.

  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 description does not need to add param info. Baseline 4 for 0 parameters is appropriate, and the description adds no param semantics.

  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 lists every agent and specifies the fields returned (name, type, channels, model, live state). It distinguishes from siblings like agent_send, which is for sending messages, and task tools.

  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 context makes clear this is for listing agents, with siblings like agent_send for sending messages, but no explicit when-not or alternative guidance is provided.

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

• task_listA
  4.4/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. Discloses default filtering (open tasks, priority order) and filterable parameters. While it doesn't mention side effects or auth, the read-only nature is implied by 'list'. Reasonably transparent for a list operation.

  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 are concise and front-loaded with the primary action. Every sentence adds value: first states action and context, second adds filters and defaults. No wasted words.

  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?

  Given no output schema, the description covers core functionality well: listing with defaults and filtering. Could add return format or pagination hint, but for a simple list tool it is sufficiently complete.

  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 has 100% coverage with basic descriptions. Description adds value by explaining defaults and ordering ('Defaults to open tasks in priority order') and clarifying how filters relate to the default list. This enhances understanding beyond bare 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?

  Description clearly states 'List tasks in the shared queue.' with specific verb (list), resource (tasks), and context (shared queue). Distinguishes from siblings like agent_list, task_create, and task_show by focusing on listing tasks with filtering.

  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?

  Description provides default behavior ('open tasks in priority order') and filtering options (status, assignee). Implicitly guides when to use (listing tasks) but lacks explicit when-not-to-use or alternatives, though sibling tools are listed for context.

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

• task_showA
  4.4/5.0
  Behavior4/5

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

  No annotations exist, so the description bears full responsibility. It discloses the returned fields and that the tool fetches details, implying a read-only operation. However, it omits explicit mention of idempotency, error conditions, or authentication needs.

  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?

  A single, front-loaded sentence that conveys all necessary information without redundancy or wasted words.

  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 simple single-task retrieval, the description is complete: it covers what the tool does, what fields are returned, and the parameter expected. No output schema exists, so the description sufficiently explains return values.

  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% for a single parameter with a clear example. The description adds context by noting accepted id formats (numeric or DIVE-N) and specifying the returned fields, exceeding schema detail.

  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 verb 'fetch', the resource 'task', and the specific details returned (status, priority, body, result, subtasks, blockers), distinguishing it from sibling tools like task_list or task_create.

  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 for fetching a single task's full details, but does not explicitly state when to avoid its use or provide alternatives. Usage is clear but lacks exclusions.

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