cos_traceability

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

With no annotations provided, the description reveals key behavioral traits: 'Read-only', 'Idempotent and non-blocking'. This goes beyond the minimal safety profile and gives useful operational context, though it does not explain what happens on failure or what 'matching evidence' entails.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, consisting of two sentences plus a scope hint. It is front-loaded with the core purpose. The trailing 'scope: task|project' is somewhat disjointed but not verbose.

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

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

The description covers purpose and key behavioral traits but lacks background on what 'doc anchors' and 'formula dispatches' represent or what constitutes 'matching evidence'. With no annotations and limited parameter explanation, it is adequate but not fully comprehensive.

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

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

Schema description coverage is 0%, and the description only clarifies the 'scope' parameter as 'task|project'. The required parameters session_id, task_marker, and persona_id are left undefined, leaving the agent with no semantic guidance beyond parameter names.

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

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

The description clearly states it is a 'read-only audit' that verifies tasks have doc anchors and recent formula dispatches have matching evidence. This specifies a concrete action and target, distinguishing it from sibling tools like cos_retrieval_cite or cos_retrieval_quality.

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

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

The description implies usage for verifying traceability and mentions it is read-only and idempotent, but it does not explicitly state when to use this tool versus alternatives or provide exclusions. No alternative tool is named, so 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.