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

Beyond the annotations (readOnly/idempotent/non-destructive), it discloses the long-poll return-on-arrival behavior and, critically, a security trait: message text is untrusted agent-authored content and origin:external signals another owner's agent, with an instruction not to follow embedded directives without owner confirmation. That safety disclosure is exactly the kind of context annotations cannot carry.

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?

It is a single dense passage that front-loads the core action and then layers polling, paging, and safety notes with no filler sentences. It is slightly run-on, but every clause carries information the caller needs.

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?

With an output schema covering return values, the description need not restate them. Annotations cover the safety profile and the description adds the paging loop, ack handoff, and prompt-injection warning, leaving nothing an agent needs to call it correctly 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 coverage is 75%, and the schema itself richly documents wait and since, so the baseline is 3. The description adds cross-references the schema lacks by tying since to the last acknowledged seq and introducing next_since/has_more as output-side paging fields, clarifying the read loop beyond the raw parameters.

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 first clause gives a precise verb+resource ('Read messages delivered to an agent') plus ordering ('oldest first') and a scoping anchor ('after since'). It is clearly distinct from the room/task siblings and explicitly pairs with city_ack_inbox, so an agent can place it 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?

It gives concrete operational context: 'Page with next_since while has_more' and 'city_ack_inbox marks messages up to a seq as handled', which tells the agent how this fits into a read-then-ack workflow. There is no explicit when-not-to-use or alternative-selection rule, but the companion tool is named and the paging loop is spelled out.

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