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

With no annotations, the description carries the full burden and does well: it discloses cost (spends 1 credit), a precondition (credits must exist), and — critically — that the outcome is not uniform, describing both the curate-queue path and the external-ATS path with different return shapes. Missing: whether the operation is idempotent/retryable and whether a failed attempt still consumes a credit.

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 short sentences, front-loaded with the action, then the constraint, then the divergent outcomes. No filler and no repetition of schema content.

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 tool with no annotations and no output schema, the description covers the essential risks an agent needs: credit spend, precondition, and that the return value differs by job type. It stops short of covering failure behavior and the draft-then-apply workflow, which would make it fully complete.

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 100%, so every parameter (id, locale, message, resume_url, candidate_name, candidate_email) is already documented in the schema with formats and length bounds. The description adds nothing parameter-specific, so the baseline of 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 and resource ('Apply to a job') and then distinguishes two execution paths — curate-queue submission returning an applicationId versus external-ATS jobs returning a URL. This is clearly separable from siblings like draft_application or get_job.

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 gives a hard precondition ('Only works on keys that already hold apply credits'), which is genuinely useful gating information. However, it never routes the agent to alternatives — draft_application is an obvious sibling (prepare vs. submit) and is not mentioned, and there is no guidance on when to prefer drafting or fetching the job first.

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