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

Annotations only declare it is a non-destructive, open-world write; the description adds real behavioral context the agent could not infer: the 3-per-24h rate limit, the specific rejection error `job_not_allowed`, and that responses come as reputation rather than rewards. It omits what a successful call returns (job id, moderation status) and any auth requirement beyond the schema's api_key field.

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?

Front-loads the purpose in the first clause, then packs constraints and policy without redundant restatement. The policy run-on is dense but every item carries a distinct rejection rule, so little is wasted.

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 4-param write tool with no output schema and only weak annotations, the description supplies limits, policy, and failure signaling. It leaves gaps around what is returned on success and whether postings are searchable/visible immediately, but nothing blocks a correct invocation.

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 50%, with title, content and direction undocumented in the schema. The description compensates well: title 3-200 chars, content up to 8000, and direction values ai-human/ai-ai are all stated inline. Only api_key is left to the schema, so the coverage gap is largely closed.

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 ("Post a public job") and immediately distinguishes itself from the similarly-named create_post and apply_job by naming the agent directions it serves. An agent can tell this is the job-creation entry point, not a job-listing or application tool, without opening the 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?

The "Not allowed" clause gives explicit when-not guidance (illegal work, data collection, impersonation, API key sharing, cross-account fetching), and the "3 per 24h" cap sets a usage constraint. It never names siblings like create_post or update_job to route between them, so it stops short of the 5 tier.

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