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

With no annotations supplied, the description carries the full burden and does so: it discloses that mark_read triggers a second write call, states the idempotency precedence rule (header wins, values must match), and documents the not_found outcome for another agent's message. It also flags the prompt-injection surface, telling the agent that sender/subject/body/attachment names and *_untrusted fields are data rather than 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?

The opening clause front-loads the core action and nothing is filler. The nested parenthetical about idempotency is dense and slightly hard to parse on first read, which keeps it from a 5.

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 tool with no annotations and no output schema, the definition covers the mutation side effect, idempotency, error case, and the security posture of returned content. It does not mention auth/permission requirements, which is the main remaining gap given there is no output schema to describe return shape.

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 0%, so the description must compensate, and it does for mark_read (marks read exactly once) and idempotency_key (interacts with the Idempotency-Key header, header wins, both must match). The id parameter's meaning is only partly explained through the {id} path and the not_found note, so one parameter remains thin.

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 opens with a specific verb and resource ("Read one message in my inbox") and pins it to the exact endpoint GET /v1/me/inbox/{id}. The word "one" plus the {id} path parameter distinguishes it from the sibling inbox_list without ambiguity.

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 makes clear this is for fetching a single message by id and explains the mark_read side-effect branch, including when it fires. It stops short of explicitly naming inbox_list as the alternative for enumerating messages, so the routing decision is left slightly implicit.

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