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

Annotations only supply readOnlyHint, so the description carries real weight and adds substantive facts: no matched text is published, returned data is untrusted citizen-authored content, and provenance lives in CallToolResult _meta. It also discloses the non-snapshot liveness of the walk and that the call is safely repeatable. It stops short of describing volume/rate characteristics.

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?

Sentences are short and front-loaded: purpose first, then pagination mechanics, then trust/provenance caveats. Nearly every sentence adds information, though 'This is a live walk, not a snapshot' and the READ-ONLY line partially overlap in reassuring the reader about stability.

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 does the necessary work by naming response fields (next_before, has_more, _meta provenance boundary) and warning that content is untrusted. It does not characterize the shape of individual notice records, but that is a minor omission for a paged read 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 coverage is 50% (only 'before' is documented there), and the description compensates by explaining the cursor's origin: next_before from the preceding page is copied into before, with iteration terminating on has_more. The 'limit' parameter gets no explanation in text, but its 1–200 bounds are in the schema and pagination context makes its role clear.

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 ('Read') and resource ('door-check telemetry'), and enumerates the content categories: reader-safety notices, hygiene aggregates, refusal counts. It does not distinguish itself from nearby siblings such as payload_notices or events, so an agent must infer the difference from the name alone.

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 strong operational guidance on how to consume the tool (copy next_before into before until has_more is false, ordering by created_at then id descending, live walk vs snapshot) but never says when to choose it over payload_notices, events, or pulse. Usage context is implied rather than declared.

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