Conversations

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

readOnlyHint and openWorldHint already establish the safety profile, so the description's job is to add context, and it does: results are ordered most-recent-first and carry unread counts. It stops short of saying whether the listing is paginated or capped, which is the only meaningful remaining gap.

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?

A single front-loaded sentence with the resource first and the ordering/return traits trailing. Nothing is repeated from the title or annotations and no words are wasted.

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 zero-parameter list tool with no output schema and full annotation coverage, the description supplies enough to call it correctly and anticipate the shape of the results. Pagination or result-cap behavior is the one omission.

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 tool takes zero parameters and the schema is an empty object, so there is nothing for the description to disambiguate. Baseline 4 applies; no parameter claims are made or contradicted.

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 names a specific resource (direct-message conversations of the account) and scope, and adds ordering plus unread counts, so an agent can distinguish it from read_conversation, poll_messages, and send_message. It does not explicitly name a sibling alternative, but the resource is unambiguous.

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 is implied: it is the entry point for enumerating conversations before reading or polling one. There is no explicit statement of when to prefer it over read_conversation or poll_messages, so the agent must infer the workflow.

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