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

The description exposes genuinely useful behavior: results include a score plus a per-question correct/incorrect flag and the correct letter, and answers are accepted only once per question_id. That last rule reads as server-side record keeping, which sits awkwardly against readOnlyHint=true, and the description never reconciles the two or says what happens on a repeat submission.

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 behavior and return shape are front-loaded, followed by the once-per-question batching rule. It is a touch dense (semicolons chaining three ideas), but every clause carries information about invocation or output.

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?

With no output schema, the description compensates by naming the return values (score, per-question correctness, correct letter) and explains that reasoning lives in the CELPass app rather than in the response. It leaves the repeat-submission/error behavior and the readOnly tension unaddressed.

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 both parameters are already documented, including the answers map example {"1": "C"}. The description only reinforces the intent of question_id ("returned with the question") and that the map should be sent whole, adding little 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?

Uses a specific verb ("Mark") with a clearly delimited resource (a learner's answers to one Reading or Listening item) and ties the input to the sibling tool get_celpip_practice_question, so an agent can separate it from get_celpip_sample_answers or get_celpip_practice_question.

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?

It gives explicit operational guidance: send all the learner's answers together because each question_id can be marked only once. It also implies the precondition that the question must first come from get_celpip_practice_question, though it never says when not to use this tool or names the sample-answers sibling as an alternative for explanations.

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