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

Annotations already declare a non-read-only, idempotent, non-destructive mutation, so the bar is lower. The description adds real value beyond them: it discloses the write side effect (the mark is saved to the student's exam.now progress) and the account/auth prerequisite, though it doesn't mention failure modes or rate limits.

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 action in the first clause, then the returns, then the persistence, then the prerequisite. The list of return fields is long but each item is informative; no filler sentences.

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, so spelling out the return payload (marks awarded/available, earned and missed scheme rows, feedback, common-mistake link) is exactly the right compensation. The account requirement and the persistence side effect round it out; only guidance on sibling choice 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 description coverage is 100%, so the parameters (part, answer, working, paper_id) are already fully documented, including the method-marks caveat for 'working'. The description only restates 'answer to one part' and adds no syntax or format detail beyond the schema, so baseline 3 applies.

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 precise verb and resource: marking a student's answer to one part against the official mark scheme, and names the mechanism (exam.now's marker). That is clearly distinguishable from siblings like get_mark_scheme, practise_question or common_mistakes.

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 student's answer to one part' and the prerequisite 'needs a linked exam.now account with marking' is a useful gate. However, it never says when to prefer this over practise_question or when to fetch the mark scheme with get_mark_scheme instead, and gives no exclusions.

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