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

Annotations are all false, so the description carries the behavioral burden. It usefully discloses that the retry is free because the credit was already charged, and that it returns the full regenerated analysis. It does not fully clarify whether the retry modifies the existing deep dive or creates a new one, but the provided behavior is still materially helpful.

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 sentences deliver the core purpose, the trigger condition, the cost behavior, and the return value with no filler. The most decision-relevant information is front-loaded.

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 one documented parameter, a clear condition, cost disclosure, and a stated return value, the description is complete for this low-complexity tool. The absence of an output schema is adequately compensated by 'Returns the full regenerated analysis.'

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 already documents the single id parameter with 100% coverage, so the baseline is 3. The description reinforces that the ID refers to a deep dive whose generation did not complete, but it does not add new parameter detail beyond the schema.

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 (retry), a specific resource (deep dive), and the precise condition under which it applies (generation did not complete: failed or stuck without a result). It also distinguishes the tool from the sibling retry_research by naming the deep dive resource explicitly.

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 tells when to use the tool: when a deep dive generation failed or is stuck without a result. It does not explicitly name retry_research as the alternative for research retries, but the resource distinction is apparent enough that an agent can infer the correct use case.

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