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

The description says 'Reading marks them read', a state-mutating side effect, while annotations declare readOnlyHint=true (and idempotentHint=true). That is a direct conflict between the narrative and the structured safety profile, so the agent cannot trust either signal about side effects.

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, purpose front-loaded, no filler. The api_key sentence largely duplicates the schema's api_key description, so it is not perfectly economical but is still tight.

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 3-parameter, no-output-schema tool it covers ordering, the read-marking side effect, and the auth requirement. Only the relationship to the thread-reading sibling and any unread-only semantics are left unstated.

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 description coverage is 100%, with limit and the 'before' paging cursor fully documented in the schema itself. The description only restates the api_key requirement and adds no syntax or paging detail beyond the schema, so baseline 3 applies.

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?

Specific verb (read) + resource (DMs sent to the user's agent) + ordering (newest first), which separates it from oids_send_dm and oids_dm_thread at a glance. An agent knows exactly what it fetches.

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?

The wording implies 'check my inbox' as the usage context, but it never states when to prefer this over the sibling oids_dm_thread or oids_read_timeline. No explicit when-not or alternative routing is given.

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