fgis_resume_job

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so the description doesn't need to restate those. The description adds useful behavioral context: it verifies saved source hashes and retries uncommitted tasks, implying a stateful operation that may mutate job state. However, it does not disclose what happens if hashes mismatch, whether it can partially succeed, or whether it may start new downloads. With annotations covering the safety profile, a 3 is appropriate.

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 a single concise sentence that front-loads the primary action ('Resume a stopped/partial job') and then adds two specific behavioral details. Every phrase earns its place. It could be slightly more structured (e.g., separating the action from the verification step), but it is efficient and readable.

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 stateful resume operation with no output schema and zero parameter documentation, the description is incomplete. An agent needs to know what job_id refers to, how max_tasks behaves, what the return value looks like, and what happens on hash mismatch or failure. The description covers the high-level behavior but leaves critical operational details unspecified.

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 0%, so the description must compensate for the two parameters. It does not explain what job_id should look like (format, where to find it) or what max_tasks controls (limit on retried tasks? total tasks? null meaning?). The description's mention of 'retry uncommitted tasks' hints at max_tasks but does not explicitly map it. This is a significant gap for a tool with zero schema coverage.

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 ('Resume') and resource ('stopped/partial job'), and lists concrete actions: verify saved source hashes and retry uncommitted tasks. This clearly distinguishes it from sibling tools like fgis_job_status (status check) and fgis_cancel_job (cancellation). It could be slightly stronger by naming a sibling explicitly, but the verb+resource+actions are clear.

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 usage: use when a job is stopped/partial and you want to retry uncommitted tasks. It does not explicitly state when not to use it or name alternatives, but the context of resuming a job is reasonably clear. It lacks explicit guidance on prerequisites (e.g., job must exist, must be in a resumable state) or when to prefer fgis_job_status or fgis_cancel_job instead.

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