Exam Check

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

With no annotations, the description carries the full load and does disclose a real side effect: submit_url + answers_path posts a test answer marked preflight. It also enumerates what is inspected (existence, decode, LUFS tolerance, metadata, page source, loaded scripts/styles). It does not mention permissions, whether the preflight submission is cleaned up afterward, or rate/cost implications.

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 gating instruction is correctly front-loaded, but the body is a run-on block of semicolon-joined clauses with no headings or parameter list, so an agent has to re-parse it to extract each argument's meaning. Nearly every clause carries information, but the delivery is inefficient.

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 10-parameter, nested-object tool with an output schema and no annotations, the description covers triggers, side effects, security-invariant checks and almost all parameters. The remaining gaps are submit_body and the concrete form of the READY/verdict reporting, the latter partly covered by the output schema.

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 0%, so the description must compensate, and it largely does: key, secrets, clips, page, choices, question, submit_url, answers_path and lufs_tol all get meaning (key's shape, clips as paths or [{label, path}], page auto-discovering clips). Only submit_body is left entirely undefined, and the choices/pairs semantics are conveyed but tangled.

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 clause gives a specific verb and resource: a preflight validator for exam pages that must pass before the page is shown. It distinguishes itself functionally from exam_eye_score/exam_picture_score by focusing on leakage (filenames, metadata, page source, key files, loudness). It never names a sibling explicitly, and the sheer density of the enumeration blurs the headline purpose.

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?

"Run before any exam page goes to the person; show it only on READY" gives an explicit trigger and a gating condition, which is more than most definitions offer. It does not say when *not* to use it or point at the adjacent exam scoring tools, so an agent must infer the boundary itself.

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