retry_extraction

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose the key mutation: the document is moved back into the pending extraction queue, and only documents in the rejected/retryable-failed state qualify. It omits permission requirements, whether re-running consumes quota, idempotency, and what becomes of the prior run_id.

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?

A single front-loaded sentence that states the object and its resulting state with no wasted words. Nothing to trim and nothing buried.

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?

An output schema exists, so return values need not be described. The critical remaining gap is the undocumented run_id parameter and the absence of any note on permissions or side effects for a state-mutating operation. Adequate for the action itself, thin 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?

Both required parameters (document_id, run_id) have 0% schema description coverage, so the schema supplies only titles. The description mentions the document conceptually but never explains run_id or how the two identifiers interact. With low coverage the description was expected to compensate and does not.

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 verb and effect (return a rejected/retryable-failed document to the pending extraction queue), which clearly distinguishes it from submission siblings like submit_extracted_signals or read siblings like get_extraction_batch. It is not a tautology and conveys the state transition. It stops short of differentiating itself from any closely adjacent sibling, but the resource and action are unambiguous.

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 phrase 'rejected or retryable-failed document' implicitly states the precondition for using this tool, and 'Explicitly' hints this is a manual counterpart to automatic retry handling. However there is no explicit when-to-use/when-not-to or named alternative among the many extraction siblings. Usage is implied rather than specified.

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