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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, but the description adds far more: the created object is inactive and must be activated by the user elsewhere, the draft lifecycle constraint, mandatory downstream actions (surface review_url, iterate review_flags), and content-restriction rules. This is real behavioral context the agent cannot get from the structured fields.

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-loaded with the core action and its draft-only scope, then constraints, then required follow-up. Every sentence carries weight, though the long enumerated compliance list makes it dense and slightly unwieldy for scanning.

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?

There is no output schema, yet the description names the return fields the agent must surface (review_url, review_flags), states the side effects and their limits, and covers content policy for the nested questions schema. Nothing an agent needs in order to call this correctly and report back is missing.

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 100%, so the baseline is 3, but the description adds substantive meaning for the questions parameter by forbidding content about age, family/pregnancy, health/disability, religion, national origin/race, sex/sexual orientation, arrests, and salary history. It does not clarify the type/rubric interplay further, so it is not a 5.

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 first sentence gives a specific verb and resource ("Create a skills assessment") plus an explicit scope qualifier: it is an INACTIVE DRAFT, not a live assessment. That is clear enough to distinguish it from the sibling create_questionnaire_draft by resource type, though the description never names that sibling or states when to pick one over the other.

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?

Strong negative guidance: it explicitly states the tool cannot activate the assessment, attach it to a job, or send it to a candidate, and points to Settings → Screening in AvaHR for those steps. It also prescribes a post-call workflow (show review_url and review_flags). It stops short of naming the questionnaire sibling as an alternative, which keeps it from a 5.

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