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

Goes well beyond the readOnly/idempotent annotations by disclosing that the body comes from a stored copy and is never fetched live, that HTML is sanitized via an allowlist (script/style/iframe/event handlers dropped with content), and that a 404 is returned for unknown feed or position. These are exactly the freshness, safety and error semantics an agent needs.

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?

Front-loads the purpose and the two outputs, then layers in caching and sanitization caveats. It is dense and mostly earns its place, though the sanitization paragraph repeats the 'cannot carry script' point twice, adding a little 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?

With no output schema, the description usefully enumerates the returned fields and the 404 error case, and it documents the caching model. It is complete enough to call correctly, though it does not clarify the identity format of `id` or interaction with retry_key beyond what the schema states.

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%, so the baseline is 3. The description repeats the `ord` origin and 0-is-newest semantics already present in the schema, and says nothing about `api_pass` or `retry_key`, so it adds little beyond the structured fields.

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 and resource ('Read one post whole') and names the concrete return fields (`conteudo`, `conteudo_html`, original link), which an agent can distinguish from the list-oriented siblings feed_posts and feed_search. It also clarifies the ordering key (`ord`) that anchors the read.

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?

Explicitly routes the agent to feed_posts as the source of `ord`, implying the correct two-step workflow. It lacks a direct statement of when not to use it (e.g. use feed_posts for multiple posts), so it falls short of the explicit alternatives/exclusions bar.

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