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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds valuable context on result shape (newest first, includes last message and unread count) and a strong behavioral constraint against proactive invocation. It stops short of describing pagination or result-size behavior.

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?

Two tight sentences, front-loaded with what the tool returns before the routing guidance. The 'only when the user explicitly asks' clause is slightly redundant with 'never on your own initiative,' costing a bit of efficiency.

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 helpfully summarizes the return contents (last message, unread count, chronological order) and covers the main usage constraint. The only real gap is the undocumented limit parameter, which leaves default and max behavior (1-50) unstated in prose.

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 67%, with only platform and unreadOnly documented in the schema; limit has no description in either place. The description mentions platform examples and unread counts, adding marginal meaning, but does nothing for the undocumented limit parameter, so it neither compensates nor misleads.

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 (List) and resource (direct-message conversations) plus scope details: connected accounts with platform examples, newest-first ordering, and returned fields. It names the sibling get_conversation as the per-thread alternative, so an agent can distinguish the two without opening schemas.

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: use get_conversation for a single thread, and use this tool only when the user explicitly asks about their messages, never proactively and never to suggest replies. This states both when-to-use and when-not-to-use, which is rare.

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