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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true, and the description reinforces the non-idempotency in operational terms ('do not retry automatically'), which is the single most important behavioral fact for this tool. It also discloses the return artifacts (inbox_url, read_token) despite there being no output schema. It omits any mention of authentication needs or the inbox's actual lifetime, which keeps it from a 5.

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, front-loaded with the creation action, then the follow-up usage and the retry caveat. Every clause carries information an agent needs; there is no filler or restatement of the tool name.

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 single-parameter creation tool with no output schema, the description covers the action, the two ways to use the result, and the non-idempotency trap. The remaining gap is the ttl_seconds parameter, whose expiry behavior and valid range are never tied to the 'temporary' claim.

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 only parameter, ttl_seconds, has 0% schema description coverage and the description never mentions lifetime control at all — 'temporary' is the sole hint, and it does not explain that the caller can tune expiry or what the default/maximum mean. With coverage at 0%, the description was expected to compensate and does not, leaving the parameter understood only from its name and numeric bounds.

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 gives a precise verb and resource ('Create a temporary receive-only inbox') plus the operational scope of it being temporary and receive-only. It is immediately distinguishable from the read-oriented siblings list_messages and read_message, which do not create anything.

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 states two concrete usage paths for the returned artifacts — open inbox_url for header-free reads, or keep read_token for MCP calls — which tells the agent what to do after creation. It also warns 'Creating again makes another inbox; do not retry automatically', a clear when-not-to-call constraint. It stops short of naming list_messages/read_message as the follow-up MCP tools, so the alternative routing is only implied.

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