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

Annotations already cover readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is well established. The description adds the useful behavioral note that the data is 'computed from the stores now,' implying a live/current snapshot. However, it does not disclose return shape, pagination, errors, or cost, so its contribution beyond annotations is modest.

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 one tight sentence with no filler. It front-loads the key idea ('Exactly what is loaded') and then compresses the output content into a compact list, earning its place entirely.

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 parameterless read-only tool, the description is fairly complete: it names the substantive output components and the live-computation behavior. However, with no output schema it leaves the response container shape (e.g., object vs. list) and count semantics unspecified, so it is not a 5.

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 zero parameters and the schema confirms this with an empty properties object, giving 100% schema coverage. A zero-parameter tool gets the baseline 4; there are no parameter semantics for the description to clarify.

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 names the resource ('coverage') and enumerates its contents: coverage sentences, corpus versions, counts, sessions, years, dates, licenses. It is specific about what the tool addresses, but it lacks an explicit verb like 'retrieves' or 'computes' and does not contrast itself with sibling tools.

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?

There is no guidance about when to use get_coverage instead of the many sibling list/lookup/search tools. The description simply states what is loaded/computed, leaving selection criteria entirely implicit.

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