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

Annotations cover the safety profile (not read-only, open-world, non-idempotent, non-destructive), so the bar is lower. The description still adds meaningful context beyond them: that only failed/cancelled/pending rows are touched, that succeeded rows are skipped, and critically that no re-billing occurs, which is the key economic behavior an agent must convey to a user.

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 short sentences with zero filler; the eligible-row scope is front-loaded and the billing guarantee follows immediately. Every clause carries information.

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 one-parameter mutation with no output schema and annotations that already declare the safety profile, the description covers scope and billing impact adequately. It doesn't say whether the whole batch is retried (implied by the single batch_id) or how partial failures surface afterward, but nothing essential for correct invocation 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?

With a single parameter at 100% schema description coverage, the schema already fully documents batch_id including its pattern. The description adds no syntax, format, or scoping detail about the parameter, so this is the baseline of 3.

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 (retry) and resource (rows on a batch) plus the exact row states affected (failed, cancelled, pending), which implicitly separates it from cancel_batch and create_batch. It does not explicitly distinguish itself from the near-twin siblings retry_carousel and retry_image_pack, which is the one remaining ambiguity.

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 implies when the tool applies by enumerating the retryable row states, and rules out succeeded rows. However, it never names or contrasts an alternative (e.g. retry_carousel / retry_image_pack for other resources, or cancel_batch if the user actually wants to stop work), so selection guidance is implied rather than explicit.

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