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

Annotations already cover readOnly, idempotent and closed-world behavior, so the bar is lower; the description still adds the key non-annotated fact that it is free and enumerates the returned payload (verdict, per-source URL, retrieval time, content hash, cited excerpts). With no output schema, this return-content disclosure is genuinely valuable, though "always returns the same package" mostly restates idempotentHint.

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?

Three tight sentences, front-loaded with purpose, then return contents, then the routing alternative. No filler and nothing the agent needs is buried.

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 no-arg sample tool with no output schema, the description supplies everything needed: what it returns, that it costs nothing and is deterministic, and which sibling to use for real queries. Annotations cover the safety profile, so no gaps remain.

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?

Zero parameters, so the baseline is 4. The description reinforces this with "Takes no arguments," which correctly sets the expectation that nothing needs to be supplied.

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?

States a specific verb and resource ("Return one real, previously produced evidence package") and immediately distinguishes itself from the sibling research_evidence by characterizing the latter as answering your own question. An agent can tell these two apart without opening either schema.

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?

Explicitly frames the use case: see what a paid call returns "before spending anything," and names the alternative (research_evidence) for real questions. What's missing is an outright "do not use this to answer your question" statement, but the routing intent is clear.

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