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

With readOnlyHint already declaring the safety profile, the description still carries the full return-shape burden because there is no output schema: it discloses that list mode omits evidence payloads while signalId mode returns full evidence, and it defines severity, n, confidence, windows, confidenceKind, nUnit and text. It even surfaces the detection methodology (last 14 days vs. the prior 28 at 95% confidence) delivered via howToRead — genuinely useful behavior an agent could not infer elsewhere.

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 tool's purpose is front-loaded in the first clause, and little is wasted given there is no output schema to explain the return fields. It is, however, a single long compound sentence with heavy parentheticals, which makes the mode-switching behavior slightly harder to extract than it needs to be.

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?

All four parameters are optional, there is no output schema, and the description compensates by covering both call modes, the return fields, the omission of evidence payloads in list mode, and the threshold explanation in howToRead. An agent has everything it needs to call this correctly without additional context.

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% (defaults, max, enum-like values for status all documented), so the baseline is 3. The description adds only modestly beyond that — the signalId-vs-list mode switch and the fact that clientId/status/limit are mutually applicable to list mode — without restating defaults or limits.

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?

Names a specific resource (the Signals inbox) and defines what a signal actually is — detected events and standing conditions such as visibility drops, competitor overtakes, GEO-score drops and dead sources — which no sibling tool name conveys. It also splits the two operating modes (list vs. single-by-signalId), so an agent can tell it apart from get_insights or resolve_signal without opening a 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?

States clearly that the default call returns the newest matching signals with filters (clientId, status, limit), and that passing signalId switches to a single-signal evidence fetch. That tells the agent how to pick between the two modes, but it names no alternative tool and gives no explicit when-not-to-use guidance (e.g., use resolve_signal to change status).

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