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

Annotations only declare non-read-only, non-idempotent, non-destructive, closed-world; the description adds genuinely new behavior: per-call cost of $0.01 with no charge on failure, and post-start immutability of questions. Scoring behavior per question type (choice/multi_choice/short_text/long_text) is also disclosed, which the schema only hints at structurally.

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?

Information-dense and front-loaded with the create/update distinction first, but the semicolon-chained clauses make it read as one long breath. Every sentence carries content — cost, immutability, scoring, content policy — so nothing is wasted, just tightly packed.

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 6-parameter mutation tool with no output schema, the description covers cost, immutability, scoring semantics, content policy, and dependency on hiring_mark_assessment. It stops short of describing what the call returns (e.g., the created test's slug) or ordering/pagination concerns, but that is a minor gap.

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 already 83%, so the baseline is 3; the description adds real meaning by clarifying that 'assessment' is an existing test's slug and by explaining how 'accept' answers drive scoring for short_text and that long_text defers to hiring_mark_assessment. It also notes time limit and shuffle are optional, though it doesn't explain the 0-means-none convention beyond the 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?

States a specific verb+resource pair (write/change a skills test) and immediately encodes the create-vs-update switch via the slug parameter. It is clearly separable from siblings like hiring_list_assessments, hiring_send_assessment, and hiring_mark_assessment, which are named or implied by their distinct roles.

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?

Explicitly covers create vs. edit ('or change one (give its slug)'), routes grading of written answers to hiring_mark_assessment, and gives a when-not rule ('questions stay fixed once someone has started the test; save a new test instead'). It also scopes content ('write tests about the job's real work; personality and IQ-style questions are not what this is for').

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