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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely valuable non-obvious semantics: the false-negative risk of an empty change set and that notice status is date-dependent and out of scope. It doesn't cover rate limits or result size limits, keeping it below a 5.

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 front-loaded sentences: purpose first, return values second, caveats last. Every sentence carries distinct information and there is no filler.

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?

Output schema exists and annotations are rich, so the description only needs to add the interpretive caveats it does add (empty result semantics, notice-status gap). For a two-parameter polling tool this is sufficient to call it correctly.

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 0%, so the description carries the burden, but the object-level schema description (not the description text) is what actually explains 'previous' as the preceding snapshot and empty-list-as-baseline. The description only alludes to 'watched set of peaks' and 'previous snapshot', leaving slug format and the baseline mechanics to the schema.

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 operation (compare a watched set of peaks against a previous snapshot) and the outputs (content changes, removals, updated snapshot). It is distinguishable from siblings like get_peak or search_peaks by its diff/stateful nature, though it never names a sibling explicitly.

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?

Gives clear context for when to use it (polling a watch list for changes) and a strong when-not caveat: 'No changes means no new source data, not proof that conditions are unchanged. Date-dependent notice status must still be checked.' That implicitly routes the agent to get_notices, though it doesn't name that tool.

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