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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world. The description adds real value beyond them: the visibility consequence of a draft (nobody can see or apply until the member publishes in the dashboard) and the response payload (job with job_id and version). It does not state that repeated calls create separate jobs, which is the main behavioral gap for a non-idempotent create.

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?

Three dense sentences that front-load the core action and its defining constraint, with no filler. Slightly cramped by the line break splitting "publishes it / in the dashboard", and the return-value note could be tightened, but every clause carries information.

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?

Annotations cover the safety profile and an output schema exists, so the description is not obligated to explain return values — it does so anyway in a useful way (version for update_draft_job). Combined with the draft visibility semantics and the threshold default, an agent can call this correctly; only the repeat-invocation behavior is left unstated.

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?

With 0% schema description coverage, the description carries the burden and does compensate for the genuinely ambiguous parameter: cv_pass_threshold is defined as the CV screen pass mark on a 0-100 scale, with explicit guidance to omit it for the platform default. title and description are left undefined, but their meaning is self-evident from the field names; the explanation of the one non-obvious parameter is what matters.

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 and resource ("Create a DRAFT job") and immediately defines what 'DRAFT' means in this system: invisible and not open to applications until published. It also names update_draft_job as the follow-up consumer of the returned job_id, so the create/update boundary is legible without opening either schema.

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?

Usage is implied rather than stated: an agent can infer this is the entry point of the job lifecycle and that update_draft_job handles later edits. However, there is no explicit when-not-to-use guidance relative to generate_job_config, nor any statement about what happens if you call it repeatedly or whether a draft must exist before publishing.

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