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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real content: it discloses what a change record contains, that each change names the archived records it compares, and it pre-empts a likely misreading by stating topics describe mentions, not stance. It does not state ordering (newest-first?) or result-size behavior, which matters for a 'recent changes' feed.

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 short sentences, front-loaded with the core purpose, then return-content detail, then a disambiguation note. Every sentence carries information; the closing topics sentence is slightly tangential but earns its place by preventing a stance-related misinterpretation.

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 work of describing returns: sentence diffs, HTTP status changes, referenced archived records, and topic semantics. What is missing is ordering/pagination behavior and any indication of volume — minor for a read-only feed but not nothing.

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 only 50%: `since` is documented in the schema, but `limit` (default 50) has no description anywhere. The description never mentions either parameter, so it does not compensate for the gap — an agent gets no guidance on pagination, max limit, or how `since` interacts with the feed.

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?

Specific verb+resource ('Get recent changes detected across all politicians') with the change types enumerated: sentence additions/removals and HTTP status changes. It clearly is not a search or a per-politician lookup, though it never names a sibling (e.g. politics_timeline or politics_provenance) that an agent might confuse it with.

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 'recent changes across all politicians' — an agent can infer this is a global changelog feed rather than a targeted query. But there is no explicit when-to-use, no when-not, and no pointer to the closest siblings (politics_timeline, politics_provenance, politics_search) that could serve overlapping needs.

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