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

With no annotations, the description carries the full burden and does substantial work: it defines the pass/advisory/fail outcome scale, states that each metric carries its denominator, discloses per-case speed, and adds the REHEARSAL marking rule for unsigned draft test sets plus the caveat that a pass is not a safety clearance. What it omits is whether a report exists only after finish_exam, and whether results are stable or can be recomputed.

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?

The metric enumeration is dense and earns its place, but the description opens with four sentences of liability boilerplate rather than the tool's function, so the actual purpose is buried mid-paragraph. The safety language is defensible for this domain but is not front-loaded around what the tool does.

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?

An output schema exists, so return structure need not be explained, yet the description still characterizes the three exam-type metric sets and the REHEARSAL/unsigned-draft caveat that an agent would otherwise miss. The remaining hole is the run_id lifecycle (obtaining it, and whether it must be a finished run), which is not covered anywhere in the structured fields.

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?

The single parameter run_id has zero schema description coverage and the description never mentions it, so nothing explains where a run_id comes from or whether it must reference a completed run. With only one obvious integer argument the gap is not fatal, but the description adds no meaning beyond the schema here.

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 the resource precisely ("The report of a finished exam") and enumerates the metrics returned for each of three exam types (catch/false-flag/abstain rates, handled rate/false alarms/unreadable replies, code recall/precision/invalid codes). This is far more specific than a restatement of the name. It stops short of distinguishing itself from siblings like get_accuracy or get_exam_cases, which also return performance data.

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?

Usage is implied by "a finished exam" and the note that a result on an unsigned draft set is REHEARSAL, which tells the agent when a report is meaningful. However, no sibling is named and there is no explicit "use this instead of X when Y" routing, so the agent must infer the boundary against get_accuracy and get_exam_cases.

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