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

With annotations declaring readOnlyHint=false, idempotentHint=false and openWorldHint=true, the description still adds substantial context: it creates an external artifact in the teacher's Drive, the data does not transit chat, Google must be connected with Sheets access, and the failure path returns a link to connect. That covers side effects, auth prerequisites, and degraded-mode behavior beyond what the annotations state.

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?

Two sentences, front-loaded with the action and artifact, followed by the auth caveat. Every clause carries information (contents, destination, return value, prerequisite, failure behavior) with no filler.

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 one-parameter export tool whose annotations already declare mutability and open-world behavior, the description covers the artifact destination, contents, return value, and the Google connection prerequisite. An output schema exists, so return-shape detail is not required, and nothing an agent needs to call it correctly 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% for the single sessionId parameter, and the schema already documents its origin (list_grading_sessions or create_grading_session) and its 24-char hex pattern. The description adds no further parameter meaning, so the baseline of 3 is appropriate.

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 ('Creates a Google Sheet of the session's results') plus the exact contents of the artifact (one row per student, scores by part, feedback links) and the return value (its link). It also implicitly differentiates from the sibling get_grading_results by stressing 'The rows never pass through chat.'

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?

Clear context for use: it explains the side effect (Sheet in the teacher's own Drive) and the contrast with tools that return rows in chat, which helps an agent pick this over get_grading_results. It doesn't name that sibling explicitly, and it doesn't cover other alternatives, so it stops short of full when/when-not guidance.

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