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

The annotations flag readOnlyHint=false and idempotentHint=false, and the description explains exactly why: it 'marks them as seen so the next check starts from now.' That discloses the state mutation and the non-repeatable cursor semantics in plain language, adding real context beyond the boolean hints.

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?

A single front-loaded sentence where every clause carries weight: what is returned, the time window, the stored-filter behavior, and the seen-marking side effect. 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?

There is no output schema, so the description correctly carries the return-value burden by naming 'index signals'. The mutation semantics are covered. Only minor gaps remain, such as the shape/format of the returned signals and behavior when no new signals exist.

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?

With one parameter at 100% schema coverage, the baseline is 3. The description goes further by clarifying that the filters are the ones 'it was saved with', i.e. the caller passes only a name and no filter arguments, which disambiguates the single parameter's role.

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 ('returns the index signals that are new on a saved watch') and scopes it by time ('since it was saved or last checked'). It is clearly distinct from the save_space_watch sibling, though that sibling is never named to make the routing explicit.

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?

Usage is implied by the time window ('since it was saved or last checked'), which tells the agent this is a polling/check operation on an already-saved watch. There is no explicit when-to-use statement, no prerequisite (e.g. that save_space_watch must have run first), and no alternatives named.

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