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

The annotations set destructiveHint=true for the whole tool, which is coarse since 'list' is read-only; the description usefully disambiguates by stating that redrive puts messages back on the queue while purge deletes them. That per-action destructiveness is real added value over the annotations. It does not mention auth requirements (the passport_token path), rate limits, or whether purge is recoverable, so it falls short of a 5.

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?

One sentence, zero filler, front-loaded with the resource and its definition before the action list. The parenthetical definition earns its place by making 'dead letter' unambiguous, and the alternatives are enumerated inline efficiently.

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 an 8-parameter, 3-required tool with no output schema, the description plus a fully documented schema covers the essentials: what a dead letter is, the three actions, and redrive modes; pagination (after/limit) and auth are handled in the schema. It leaves out what the list operation returns and whether purge is irreversible, which is a minor but real gap.

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 100%, and the schema already labels 'all' as 'redrive: every dead letter' and 'ids' as 'redrive: these messages', so the description's 'ids, or all' is largely a restatement. It adds no format, limit, or pagination detail beyond the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

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 names a specific resource (a queue's dead letters) and defines precisely what qualifies as a dead letter ('messages claimed max_attempts times without an ack'), then enumerates the three verbs it supports (list, redrive, purge). This distinguishes it cleanly from the surrounding queue_* siblings (queue_ack, queue_nack, queue_claim, queue_put) without needing to name them.

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 clear context for when this tool applies: the messages are dead letters that have exhausted max_attempts, so an agent can tell this is the recovery path rather than the normal claim/ack flow. The three actions and the redrive modes ('ids, or all') are spelled out. It stops short of explicit when-not guidance or naming alternative siblings, so it is not a 5.

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