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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, but the description adds real operational context beyond them: the refusal cases and the prerequisite step are not derivable from the structured fields. It stops short of saying what a successful restart actually triggers (immediate re-submission, async retry, credit cost) or what is returned, which keeps it from a 5.

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, front-loaded with the qualifying states, then the prerequisite, then the refusal conditions. Despite the em-dash list, every clause carries decision-relevant information with no filler.

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 single-parameter mutation tool with no output schema, the description covers the trigger conditions, prerequisites, and refusal cases well. The remaining gap is what to expect after a successful retry (state change, timing, or how to confirm progress via auto_apply_get/auto_apply_list), which is left implicit.

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?

Only one parameter, job_slug, and the schema already documents it at 100% coverage including where to obtain it (search_jobs, my_jobs). The description adds no further meaning about the identifier, so the baseline 3 applies.

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/refresh) on a specific resource (an automatic application) and enumerates the exact states that qualify: stopped on an unanswered question, after repeated errors, CV not tailorable, or awaiting review. This clearly separates it from auto_apply_start, auto_apply_review, and auto_apply_cancel.

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?

Gives explicit preconditions (answer open questions via answer_bank_save or screening_answers_set first) and explicit exclusions (refused for a declined attempt or one that may already have reached the employer). An agent knows both when to call it and when the call will fail.

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