job_retry

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds a meaningful validation rule about revision currency, but omits what a retry does to existing partial outputs, whether it resumes or restarts from scratch, and what error surfaces on a stale revision.

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 efficient sentence with the core action front-loaded and the precondition trailing it; no redundant wording. It is short enough that a little more structure (when-not guidance) would have cost nothing.

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 mutation-flavored retry operation with no output schema and half the parameters undocumented, the description covers the essential precondition but leaves out outcome behavior and the failure path. It is minimally sufficient for correct invocation but not for understanding consequences.

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 coverage is only 50%: projectDir is documented in the schema while jobId is not. The description adds no parameter-level detail beyond loosely implying that jobId names the job and projectDir is the project whose revision matters, so it fails to compensate for the undocumented parameter.

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 (restart) and resource (a failed or interrupted job), which clearly separates it from siblings like job_cancel, job_get, and job_list. It does not explicitly name an alternative tool, but the action is 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?

Provides a concrete gating condition: only retry when the original project revision is still current. That is real when-to-use guidance rather than implication, but it never says what the agent should do instead when the revision is stale (e.g., restore a revision or re-create the job).

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