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

Goes well beyond the annotations: it discloses that this is a mutating, asynchronous operation that creates a submission record, returns only a submission_id, and requires polling submission_get for grades. It also explains that results stream live into the teacher's editor, which the non-idempotent/create semantics alone would not convey.

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?

Three sentences, no filler, with the core action first, then required inputs, then the async-return caveat front-loaded before an agent would try to read grades from the response.

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 create-and-grade tool with an output schema, the description covers what an agent needs to call it correctly: inputs, mutation semantics, and the fact that the response is a submission_id requiring a follow-up poll. Nothing material 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 coverage is 100%, so the schema already documents exam_paper_id, answers, question_number and answer_text in detail. The description only restates that answers are keyed by question_number, adding no format or constraint detail beyond the schema — baseline 3.

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 and resource ('Mark a student's typed answers against an existing exam paper') and names the canonical grading path, which clearly separates it from submission_get, markResult_get and results_get. An agent can tell exactly what this tool produces without opening the schema.

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 states the prerequisite (an existing exam paper via exam_paper_id) and names the follow-up tool ('poll submission_get'). It does not state when *not* to use it (e.g. use a different tool for pre-existing submissions or non-text input), so it stops short of full routing guidance.

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