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

Annotations only declare readOnlyHint=false, so the description carries real weight and delivers: retry-after-backoff behavior, a three-attempt cap before human review, and the safety condition for retryable=false. It does not spell out what the failure record contains or how the human-review escalation surfaces, but the operational retry policy is well disclosed.

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 tight sentences, front-loaded with the core action and then the retry policy. Every sentence carries distinct information; nothing is filler.

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 an output schema present, return values need no explanation, and annotations cover the write semantics. The description adds the retry ladder and escalation rule an agent needs to call this correctly. Nothing material is missing.

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 every parameter (including the retryable default and retry_after_seconds range) is already documented in the schema. The description restates the retryable=true/false policy rather than adding syntax or constraints, 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?

States a specific verb and resource ('Record a failure under your active lease') that clearly separates it from agent.inbox.complete and agent.inbox.progress in the same family. An agent can identify the operation 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?

Gives concrete when-to-use guidance: set retryable=false when automatic retry would be unsafe or the external send is uncertain. It implies but does not explicitly name the sibling to use for successful completion, so routing guidance is strong but not fully framed against alternatives.

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