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

Goes well beyond the readOnly/destructive annotations: it discloses that reading does not mark anything read and the unread count is preserved on both sites, that the call requires the messages:read permission on the member's behalf, and that unconnected members are prompted to sign in. It also carries an explicit prompt-injection warning that member-authored text is data, not instructions.

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 what the tool does before adding the unread-state, permission, and auth caveats, which is the right ordering. It runs long with product-specific framing ("the conversation door the Messages page uses", "Automate America") and a generic safety sentence, but none of it is truly wasted given the mutation-adjacent risks being ruled out.

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 specifies the return shape: one thread's messages, oldest first, with people named by first name; pagination is covered by cursor/limit in the schema. Reasonably complete, though it never states what an empty or not-found conversation returns.

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 limit, cursor, and the negative-id convention for hidden-poster customers are already fully documented in the schema. The description adds only the minor detail that each person is named by first name; it contributes nothing about the required userId beyond what the schema states.

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 conversation") and scopes it to messages between the member and exactly one person, oldest first. This distinguishes it implicitly from list_my_threads, though it never names that sibling explicitly, so an agent must infer the split between listing conversations and reading one.

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?

Usage context is implied rather than stated: it reads a single thread without consuming unread state, which tells the agent it is safe to poll. It does not say when to prefer list_my_threads first, nor does it state what happens with an invalid or nonexistent userId, leaving the routing decision to inference.

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