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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false. The description usefully adds the post-call fate of messages (requeue after delay_seconds, or dead-letter after max_attempts claims), which is genuine behavioral context, but it omits lease validity requirements, what a repeat nack does given non-idempotency, and any auth/passport notes.

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?

A single tight sentence that front-loads the negative-outcome framing and states both branches. It is efficient, though the 'Not done:' fragment is slightly oblique and costs a little immediate clarity.

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?

No output schema exists, and this is a 6-parameter queue mutation with non-trivial retry/dead-letter semantics. The description covers the core outcome but says nothing about the return value, the source of max_attempts (queue_settings), or how leases interact with the requeue, leaving gaps an agent would need.

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%, so all six parameters are already documented in the schema, including delay_seconds ('Wait this long before it can be claimed again'). The description references delay_seconds in context but adds no syntax or format detail beyond the schema, so the 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 conveys the tool's effect: messages are returned to the queue for another claim or pushed to the dead-letter list, which is the essence of a negative-acknowledge. It relies on the title for the verb ('Return... for a retry') and does not differentiate from siblings such as queue_ack, queue_dead, or queue_extend, so it tops out at 4 rather than 5.

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 'Not done:' lead implies the condition for use (you failed to finish processing the leased messages), but there is no explicit when-to-use vs. queue_ack (success path) or queue_dead (dead-letter inspection). Usage is implied rather than stated.

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