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

Beyond the readOnlyHint annotation, the description explains nuanced internal behavior: queued/retrying deliveries read from a live copy while terminal ones read from durable storage, yet response shape remains identical. It also details what each field means (status, attempt, timestamps, terminalError, callbackState) and the meaning of unavailable reasons, giving agents deep insight into what to expect when invoking the tool.

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 front-loaded with the main purpose in the first sentence, then expands into behavioral detail. It is dense but each clause adds meaningful information about response fields, statuses, or alternatives. A slightly more structured format (e.g., bullets for field lists) could enhance skimmability, but the prose is efficient and well-ordered.

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 carries the full burden of explaining return values, and it does so exhaustively: it covers both terminal and non-terminal delivery states, the exact field names and their types, the conditions for unavailable reasons, and even mentions the callbackState field. This is complete enough for an agent to correctly parse and act on the response without further documentation.

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 input schema already fully describes requestId with source (202 responses, list_requests rows) and required status. The description's reference to 'the same requestId a 202 response returned' adds no new parameter-level semantics beyond reinforcing the polling pattern. Schema coverage is 100%, so baseline 3 applies.

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 opens with a clear, specific verb+resource statement: 'Get every target this request fanned out to, each with its delivery receipt or the reason it has none.' This distinguishes it from siblings like get_request and list_requests, clarifying its unique scope as a receipt/log inspection tool rather than a general request fetcher.

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 explicitly says 'poll this on an interval with the same requestId a 202 response returned,' providing concrete guidance on when to use it (polling after a 202). It also names an alternative for sync_or_stream_delivery targets: 'see the response body from that call instead.' This gives both when and when-not guidance.

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