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

With no annotations, the description carries the full behavior burden. It does add valuable context about ordering, cursor pagination and the trust boundary for sender/subject/body/attachment names, but it says nothing about authentication, rate limits, or what the result envelope looks like beyond the untrusted fields.

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 sentences, purpose front-loaded, and the untrusted-data warning is compact and relevant given that message content comes from external agents. Dense but each clause earns its place; the security sentence is somewhat long but not padded.

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 four-parameter, no-output-schema, no-annotation list tool, the description covers purpose, ordering, pagination and trust handling, and implies the returned fields. It still leaves the agent without default limit, since format, or the shape/size of the returned page, which matter for correct paging.

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 0%, so the description must explain all four parameters. It mentions unread, since and cursor at a high level but gives no formats, defaults or bounds (e.g. that since is an ISO-8601 UTC timestamp, that limit caps at 200), and limit is not mentioned at all.

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 and resource ('List my inbox') plus ordering ('newest first'), filters and pagination, and pins it to the concrete endpoint GET /v1/me/inbox. It is clearly a list operation versus the sibling inbox_read, though it never names that sibling to make the split explicit.

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 by 'List my inbox ... with unread/since filters and cursor pagination', which tells the agent this is the paged, filterable listing call. There is no explicit when-to-use versus inbox_read, no statement about prerequisites or auth, and no exclusions.

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