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

Annotations already declare safety traits (read-only, idempotent, non-destructive). The description adds meaningful context: it returns 'published' (precomputed) data and explains that a discrepancy does not prove either source wrong, requiring human review. This goes beyond annotation coverage.

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?

Two sentences: the first front-loads the core functionality and contents, the second adds an important interpretive caveat. No fluff or repetition.

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?

For a simple read-only retrieval tool with a well-described parameter, rich annotations, and an output schema, the description covers the essential return contents and caveats. The existence of an output schema means return format details are not required here.

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 covers the single parameter fully with examples and clarification ('id or name'). The tool description adds no additional parameter semantics, so baseline 3 is appropriate.

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 the tool returns a cross-source reconciliation group for a dataset name or id, listing specific contents (counts, dates, statuses, etc.). This distinguishes it from sibling tools focused on anomaly detection or evidence verification.

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 via 'published' and the reconciliation context, but does not explicitly state when to prefer this tool over alternatives like find_anomalies or verify_evidence. The caveat about human review provides interpretive guidance but no direct when-to-use/not-use instructions.

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