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

Annotations already indicate readOnly, openWorld, and idempotent behavior. The description adds useful behavioral detail beyond annotations: items are deduplicated, sorted newest first, text is bounded, and the discovery ladder runs and reports how the URL resolved. This helps the agent anticipate output shape and edge cases.

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 sentences, with the core behavior front-loaded and every clause contributing useful information. The output field list is compact and the use case is stated last without redundancy.

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 covers the output format, ordering, dedup, date filtering, URL flexibility, and resolution reporting. The schema fills in parameter details for since, max_chars, and task_context. It is mostly complete for a read-only tool, though it could briefly mention that limit defaults to 20 and max 100.

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 80%, so a baseline of 3 applies. The description adds meaningful param-related nuance: it explains that url may be a feed URL or a plain site URL and that a discovery ladder resolves it. It also implicitly describes the 'since' behavior and bounded text, though it does not mention limit or max_chars by name.

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 uses a specific verb ('Read a feed') and a clear resource, enumerates the returned fields, and states ordering, dedup, and optional date filtering. It also gives a concrete use case ('what is new on X'), which distinguishes it from siblings like feed_find and news_search.

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 explicitly says 'Use for "what is new on X"', giving clear context for when the tool is appropriate. It also clarifies that url can be a feed URL or a site URL, but it does not explicitly contrast with feed_find or news_search or state when not to use this tool.

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