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

Annotations already signal readOnly/idempotent/non-destructive, but the description adds real behavioral context by emphasizing it never starts or charges anything and that retry requires a new batch and fresh quote plus human approval. This is meaningful workflow detail beyond the safety hints, though it doesn't describe the shape of the plan returned.

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?

Two tight sentences with the read-only guarantee and workflow constraints front-loaded; no filler. Could be marginally improved but every clause earns its place.

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, the description needn't explain return values, and annotations cover the safety profile. It adequately conveys purpose and the no-charge/no-start guarantee, though the undocumented 0%-coverage parameters leave a gap for a tool the agent must populate correctly.

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 coverage is 0%, so the description must carry parameter meaning, but it only loosely implies batch_id ('of one batch') and scenes ('failed scenes'). It says nothing about the lang parameter, the request_id field, the 10-scene cap, or why scenes must be enumerated.

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+resource+scope: 'Read-only recovery plan for terminal failed scenes of one batch.' This distinguishes it from mutating retry/execute siblings by asserting it never starts or charges anything, though it doesn't name a specific alternative tool.

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?

Explains the condition it serves (terminal failed scenes of a batch) and, crucially, what any actual retry would require (NEW batch ID, fresh exact quote, separate human approval), steering the agent away from assuming this performs a retry. It stops short of naming the sibling tools to use for the subsequent retry/quote steps.

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