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

Annotations already cover read-only, non-destructive, closed-world, so the description is free to add real value: it discloses ordering ('oldest first'), content transformation (HTML-only bodies converted), the presence of a 'links' field, and a prompt-injection warning that every message is untrusted external content. That last point is operationally important behavior no annotation conveys.

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 what is returned and how to obtain the id, with the safety warning given explicit emphasis. The parenthetical about HTML conversion is slightly clunky but carries information, so there is little waste.

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 necessary work of sketching the return shape (ordered messages, bodies, links). It stops short of covering limit behavior and empty/missing-thread cases, which is the main remaining gap for a two-parameter read tool.

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?

The thread_id guidance duplicates the schema description almost verbatim, adding no new meaning. The limit parameter is never mentioned at all, and given 'oldest first' ordering, an agent has no way to know whether limit truncates the newest messages — a meaningful gap at 50% schema coverage.

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 resource (a whole conversation/thread) and its scope: 'Every message in one conversation, oldest first,' which clearly separates it from a single-message fetch. It also says where the thread_id comes from, but never names the sibling it is not (e.g., mail_get_message), so the differentiation is inferred rather than stated.

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?

Gives a concrete prerequisite: 'Take thread_id from mail_list_threads,' which routes the agent correctly when it does not already have an id. It does not state when to prefer this over fetching individual messages, nor what happens for an unknown thread, so the guidance is clear but not exhaustive.

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