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

With readOnlyHint: true already in the annotations, the description adds valuable behavioral detail beyond the annotation: results are sorted newest-first and paginated via cursor. This is precisely what an agent needs to consume the feed correctly. It doesn't cover response shape or filter semantics, but those are secondary for a read-only list endpoint.

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?

Two sentences with zero filler. The 'newest-first, cursor-paginated' behavior is front-loaded right after the short verb+resource statement, giving the agent the most decision-relevant information first without any wasted words.

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?

The description is adequate for a straightforward read-only listing where all parameters are self-documented, but it is thin in a few areas: no output schema exists, the description does not clarify whether the fully documented anomaly items (or a feed of metadata) are returned, and the combination semantics of multiple filters (e.g., host vs detector; AND or OR?) is left unexplained.

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%, so the baseline of 3 applies. All eight parameters are individually documented in the schema (host, seat, grade, limit, since, cursor, detector, acknowledged), and the description itself adds no parameter-level context that isn't already in the structured input.

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?

The description states a specific verb ('List') and resource ('anomalies') and adds defining traits: the newest-first, cursor-paginated anomaly feed. This clearly distinguishes it from get_anomaly (single-item fetch), but it does not explicitly differentiate it from the similarly named sibling list_software_anomalies.

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?

No explicit when-to-use guidance is provided. The description does not explain when to choose this over list_software_anomalies, get_anomaly, or other list tools, nor does it state the default feed scope or how filters should be combined. The usage context is only implied by the 'feed' phrasing.

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