config_recover_kit_attempt

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

Annotations already mark the tool as destructive and not read-only, so the description does not need to restate that. It adds useful behavioral context beyond the annotations: the action is local-only, affects exactly one attempt, and cannot recover durable jobs. This meaningfully informs the agent about scope and limits.

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 two sentences with no filler. The core action and precondition are front-loaded, followed by a sourcing instruction and a clear limitation. Every sentence adds value.

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 a destructive, local-only recovery action with a nested execution object, the description gives the essential context: the prerequisite, the scope, and the source for the required identities. It does not describe the response shape or failure modes, but there is no output schema and the instructions are practical enough for correct invocation.

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 schema has 0% description coverage, so the description must compensate. It partially does by instructing the agent to copy 'execution and attempt identity' from local session_get output, which maps to attemptId and execution. However, it does not explain provider choice, sessionId sourcing, or the acknowledgement field beyond what the schema's literal constants already convey. The guidance is helpful but incomplete for all five parameters.

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 action ('Fence and release'), a specific resource ('one exact unadmitted durable Kit attempt'), and a key precondition ('after the previous gateway process has been stopped'). It also disambiguates itself by stating it 'cannot recover an existing durable job.' This is enough for an agent to identify what the tool does and how it differs from other recovery-related tools.

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 clearly states when to use the tool: only for one exact unadmitted attempt and only after the previous gateway process has been stopped. It also gives an explicit exclusion ('cannot recover an existing durable job') and tells the agent where to source values ('from local session_get output'). It does not name a specific sibling alternative, but the when/not-when guidance is strong.

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