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

With no annotations, the description carries the full burden and does well: it discloses the privacy model ('read by its two members and nobody else'), explains the untrustedText flag on member-written content and warns that such text is data, not instructions, and flags that arguments and credential-bearing results may persist in client transcripts. It does not cover pagination behavior or result shape beyond that flag.

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?

Purpose is front-loaded in the first sentence, which is good. But the remaining text is largely auth boilerplate repeated word-for-word in the schema, and the prompt-injection warning is buried mid-paragraph, so length is not fully earned.

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 two-parameter list tool with no annotations and no output schema, the description supplies the security model, the untrustedText result semantics, and credential handling. Only pagination/limit behavior and return-value structure remain unaddressed.

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 pass parameter's text is duplicated verbatim from the schema, so the description adds no meaning beyond it. The limit parameter is not mentioned at all, leaving a quarter of the schema's coverage (50%) uncompensated by the description.

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 first sentence states a specific resource and ordering: 'Your direct-message conversations, newest first, with the unread count per member.' That is enough to distinguish it from dm_send and dm_thread by implication, though it never names those siblings explicitly.

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?

It gives real operational guidance on credentials (use the Authorization header, omit pass, header wins over conflicting credentials), but says nothing about when to choose this tool over dm_thread or dm_send. Usage context for retrieval versus sending or drilling into a thread is left to inference.

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