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

Annotations already establish readOnly, non-destructive, closed-world behavior, so the bar is lower. The description nonetheless adds real value beyond them: it enumerates the returned fields (ids, title, copy, href, reason, action) and states explicitly that no file body is included and nothing is sent or approved. That clarifies payload scope and the human-in-the-loop boundary, which annotations do not convey.

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 short sentences, front-loaded with what is listed and immediately followed by return-field scope and the no-side-effects guarantee. Every sentence carries distinct information with no repetition of the title or schema.

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 no parameters and no output schema, the description compensates well by listing the returned fields and ruling out file bodies. What remains unstated is ordering, pagination, or emptiness behavior for the queue, but for a zero-argument read listing the definition is close to sufficient.

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 tool takes zero parameters, so there is no parameter meaning to add and the baseline is 4. The schema is effectively empty and imposes no ambiguity the description would need to resolve.

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 concrete verb and resource: list Underwrite items requiring human attention. The 'Underwrite' qualifier distinguishes it from the sibling queue tools (list_book_person_queue, list_second_look_inbox, list_originator_leads), though the description never explicitly contrasts with them. An agent can identify the domain but must infer the routing rule from the queue name alone.

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?

'Items that need a person' implies the condition for calling it and the closing line 'A person still decides. Does not send or approve.' signals that this is an intake step rather than an action step. However, there is no explicit when-to-use versus the sibling queue tools and no stated prerequisites or follow-up path (e.g. open_case, prepare_decision).

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