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

Beyond annotations, the description adds important behavior: no new transcription or charge occurs, the task remains the same, and unknown submission outcomes stay held. This materially helps the agent understand cost and failure-handling behavior, though permissions and return behavior are not described.

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?

The description is two sentences and front-loads the core action of resuming a failed accepted task. Every phrase adds useful information about scope, cost, or held outcomes, with no wasted wording.

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 recovery tool with no output schema, the description covers the key behavioral context: same-task recovery, no new charge, and held handling for unknown outcomes. The main remaining gap is that job_id provenance and format are not explained.

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 has 0% description coverage and only one required parameter, job_id, but the description never explains what job_id should contain or where to obtain it. It only implies that it identifies the accepted band task, leaving the parameter largely undocumented.

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 and resource: 'Resume an accepted band task that failed, as the same task.' It also clarifies that recovery uses a saved result or known supplier job, which distinguishes it from starting a new transcription, but it does not explicitly name a sibling tool such as transcribe_again.

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?

It clearly indicates the triggering condition: an accepted band task that failed should be resumed as the same task. It also notes that an unknown submission outcome remains held for review, giving a relevant edge-case constraint, though it does not explicitly list exclusions or name alternative tools.

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