job_evaluate

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

With no annotations, the description carries the full behavioral burden and does a good job: it discloses the internal pipeline (open check, language/location/work-rights/red-flag/integrity gates), that the covered/partial/gap classification is 'decided by code' rather than model judgment, and that the outcome is a verdict with a reason. It omits side effects (whether the evaluation is persisted), relative cost/latency of a 'full evaluation', and what happens when the posting is closed or a gate hard-fails.

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?

It is front-loaded with the purpose and then enumerates the stages, with parenthetical glosses for jargon like the gate list and the tri-state table, followed by a short directive. It is dense but every clause carries information; only the arrow notation is slightly cryptic.

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 tool with no annotations and no output schema, the description supplies what is otherwise missing: the verdict enum (apply/consider/skip), the reason field, and the stage sequence. The remaining ambiguity is whether the requirement → evidence table itself is returned or only the verdict, which matters since no output schema exists to answer it.

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?

There is one required parameter with 0% schema description coverage; the description implies it identifies the single posting being evaluated ('one posting') but adds no format, validity, or lookup semantics for job_id. The meaning is inferable from the phrase, so this is adequate but not compensating for the empty schema.

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?

The description names a specific verb and resource ('Full evaluation of one posting') and enumerates exactly what the evaluation consists of: open-status check, five named gates, a requirement → evidence table, and a verdict. That is far beyond a restatement of the name. It stops short of 5 because the nearest sibling, job_score, is never mentioned, so the agent cannot tell from this text how this differs from scoring.

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 explicit sequencing instruction 'Use before pack_create' tells the agent exactly where this tool sits in the workflow, which is real routing guidance. It does not say when NOT to use it, nor name job_score or job_get as cheaper alternatives for a quick look, so exclusions are missing.

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