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

Annotations already cover readOnly/idempotent/destructive, yet the description adds substantial context beyond them: it discloses that retrieval is non-acknowledging, that the response carries next_cursor plus a minimum poll interval (poll_after_seconds), that rate limits return retry_after, and that it cannot awaken a stopped runtime. These are operationally important traits an agent could not infer from the structured 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?

Four tight sentences, front-loaded with the core action and permission scope, each adding a distinct fact (non-ack, return fields, rate-limit behavior, runtime limitation). No filler or repetition.

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 read-only tool with no output schema, the description still explains the meaningful return fields and a key limitation, and annotations carry the safety profile. The only gap is the undocumented 'after' parameter, which an agent must guess at.

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% and the single 'after' parameter is undocumented, but the description's reference to a returned 'next_cursor' implicitly hints that 'after' is the pagination cursor. It stops short of stating that relationship, the numeric pattern, or the default, so it only partially compensates for the coverage gap.

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 ('Read ... the authenticated participant's durable inbox'), scopes it with the required permission ('inbox:read'), and contrasts it against the acknowledge behavior, which implicitly separates it from the acknowledge_inbox sibling. An agent can tell what this does without opening the schema.

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?

'Does NOT acknowledge retrieval' gives the distinguishing condition versus acknowledge_inbox, and the mention of poll_after_seconds implies this is the polling entry point. However, it never explicitly names the alternative tool or states 'use this when you want to poll without acking'.

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