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

Annotations already declare idempotentHint=true and destructiveHint=false, yet the description adds real value: it preserves accepted clips, returns the recovery batch ID, and -- critically -- may spend account credits and must be retried with the identical idempotency key. This cost and retry context goes beyond the structured hints.

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?

Three tight sentences, front-loaded with the action, followed by a side-effect/return note and then cost/retry semantics. Every sentence carries distinct information with no 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?

For a credit-spending mutation tool with full annotation coverage and an output schema, the description supplies the important extra context (credit cost, idempotent retry, preservation of accepted clips). The remaining gap is the under-documented workspaceId and targetClipCount parameters.

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 only 25%; batchId's 'UUID string' is trivial and workspaceId, idempotencyKey, and targetClipCount are undocumented in the schema. The description recovers some meaning for idempotencyKey (retry semantics) and hints at targetClipCount ('missing clip count'), but leaves workspaceId and the count's 1-30 bound unaddressed.

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 states a specific verb (recover) and resource ('a terminal batch's missing clip count') plus the mechanism ('persisted recovery workflow'), which is well beyond a tautology. It does not explicitly distinguish itself from close siblings like clips_repair or clips_reselect, so it stops short of a 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?

Guidance is implied: use it on a 'terminal batch' with missing clips, and it warns that credits may be spent and that retries must reuse the idempotency key. However, it never states when to prefer this over clips_repair, clips_reselect, or clips_create, and gives no prerequisites.

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