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

With no annotations provided, the description carries the full burden. It discloses that refresh reruns discovery without creating or rate-counting a second request, that refresh is cooldown- and attempt-limited, that the tool cannot confirm for an owner, and that the token must not be placed in a URL. These are meaningful behavioral traits beyond the basic read operation. It does not explicitly state idempotency or the response format, but the read nature is clear. This is strong disclosure for a tool with zero annotation coverage.

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?

The description is multi-sentence but front-loads the core purpose in the first clause. Every sentence adds functional information: parameter conditions, rate limits, a limitation, and a security warning. There is no fluff or repetition. It is slightly dense but appropriately scoped for the complexity of the tool. It earns its length.

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?

Given there is no output schema, the description could have described the return format, but for a read tool that primarily reports lifecycle state, that is not critical. It covers the key execution aspects: input requirements, refresh conditions, rate limits, ownership confirmation limitation, and token handling. It does not mention prerequisites like authentication, but the sibling tools context suggests this is a safe read operation. Overall, it is sufficiently complete for an agent to invoke it correctly.

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 compensate. It explains the semantics of refresh (when to set true, side effects such as rerunning discovery without creating a new request) and clarifies that the request_token is the token argument (not a URL). It does not explicitly describe request_id, but its role as a UUID for the request is self-evident from the name and context. The description adds meaning to two of three parameters, significantly compensating for the schema's lack of descriptions.

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 clearly states the tool reads a specific resource: the 'private persisted route or owner-confirmed escalation lifecycle' for a given AgentWork request ID. The verb 'Read' unambiguously indicates a non-mutating operation, and the mention 'cannot confirm for an owner' distinguishes it from sibling action tools like resolve_blocker or report_blocker_outcome. It is specific enough that an agent can differentiate 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?

The description provides explicit conditions for using the refresh parameter ('only when an unselected route remains unresolved and current executable supply may have changed') and warns of cooldown/attempt limits. It also gives a security directive for the request token ('never a URL'). However, it stops short of explicitly contrasting this tool with each sibling, though it implies it is for reading only and cannot confirm for an owner. This is clear usage guidance with a minor gap in naming alternatives.

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