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

Annotations already establish readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds the capping behavior (top_n default 20, max 50), which is useful, but says nothing about auth requirements, rate limits, or pagination. Modest added value over the structured fields.

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 with no waste, and the core metric definition is front-loaded ahead of the top_n cap detail. Efficient and readable.

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?

With no output schema, the description helpfully explains what each datapoint represents (percentage of analyzed responses citing a source per bucket). It does not explain the interval requirement or return structure more fully, but it is adequate for a read-only analytics tool.

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 100%, so the schema already documents all nine parameters thoroughly. The description only restates the top_n cap, adding no syntax or format detail beyond the schema. Baseline 3 is appropriate when the schema carries the load.

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 computed metric: the percentage of analyzed responses per bucket that cited any URL from each top source. Verb/resource/scope are clear, and it is distinguishable from get-source-url-usage-time-series-tool (per-source vs per-URL). It stops short of naming that sibling explicitly, so it's a 4 rather than a 5.

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?

No explicit when-to-use or when-not guidance, and it never mentions alternatives like the URL-level or analytics (non-time-series) siblings. Usage is only implied by the time-series framing and the 'bucket' language; the interval requirement is stated in the schema, not the description.

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