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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context: 'CF-robust: fetches directly and falls back to a proxy if the source blocks the gateway.' This explains network resilience behavior and normalization, which are not inferable from annotations. It stops short of describing return structure or error handling, but given annotation coverage, this is sufficient.

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 description is two sentences: the first states purpose and scope, the second adds usage guidance and a resilience behavior. Every word earns its place, with no filler or repetition of schema/annotation content. The front-loaded verb 'Fetch' immediately signals the tool's action.

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?

For a tool with only three parameters (all documented) and strong annotations, the description provides sufficient context: what it fetches, how it handles network failures, and a recommended workflow. It does not mention the return format, but there is no output schema, and the behavior of 'normalize' hints at content processing. The only notable gap is not addressing the sibling read_feed, which might be a natural alternative for already-listed feeds, but the guidance to use list_feeds first partially mitigates this.

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 100%: all three parameters (url, limit, query) have descriptions in the schema. The description itself adds no parameter-specific information beyond the schema; it only mentions normalization and proxy fallback, which are tool-level behaviors. Therefore, the baseline of 3 is appropriate; the description does not need to compensate for schema gaps.

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 opens with a clear verb-object pair: 'Fetch and normalize any RSS / Atom / RDF feed by URL.' It immediately conveys the tool's scope (any feed format) and its core action (fetching and normalizing). The phrase 'any RSS / Atom / RDF feed' distinguishes it from sibling tools like list_feeds, which is explicitly referenced, and read_feed, which likely has a narrower purpose.

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?

The description provides a concrete workflow hint: 'Use list_feeds first for curated sources.' This tells the agent when to call list_feeds before fetch_feed, implying that fetch_feed is for arbitrary or unsourced URLs. However, it does not explicitly mention when to prefer read_feed or other alternatives, and the exclusion is implicit rather than stated as a hard rule.

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