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

Beyond the readOnlyHint annotation, the description discloses critical behavior: internal drafting is disabled, the tool asks the model to draft in the same call when sampling is supported, and it returns a refusal otherwise. This is exactly the kind of behavioral context that prevents wasted calls and confusion.

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 purpose statement is front-loaded and the critical usage caveat follows cleanly. Every sentence serves a distinct function: what the tool does, the sampling condition, the failure behavior, and the fallback workflow. No filler or redundancy.

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?

Given zero parameters, an existing output schema, and annotations declaring read-only behavior, the description covers the main non-obvious context: when the tool will refuse and how to complete the workflow using sibling tools. Nothing essential is missing for correct invocation.

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?

The tool has no schema parameters, so there are no parameter semantics to clarify. With 100% schema coverage and zero parameters, the description needs to add nothing for parameter understanding; the baseline 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 uses a specific verb ('surface') and clearly identifies the resource ('payroll and deduction anomalies') and scope ('in the latest snapshot'). This separates it from sibling tools such as query_fact, run_sql, and compare_departments.

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 explicitly states when to use the tool and what to do when it cannot be used: if the client supports MCP sampling, use this tool; otherwise it will return a refusal, and the agent should use ask_prepare then ask_submit_draft. This is concrete, actionable usage guidance with a clear alternative path.

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