canvas_submission

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

Annotations already establish readOnly, idempotent, non-destructive and closed-world behavior, so the description only needs to add beyond that. It does so usefully by disclosing a side effect that is not captured by any annotation: consultation leaves feedback unread, plus it clarifies that non-current attempts and what-if scores are included rather than just the latest 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?

Two short sentences, zero filler. The payload enumeration comes first and the one caveat is appended compactly with no restatement of the title or name.

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 usefully compensates by listing what the call returns. Minor gaps remain: it says nothing about paging through a long submission history despite the page parameter, and nothing about how raw mode changes the result. Those are small for a read-only tool whose parameters are fully documented.

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 course_id, assignment_id, raw and page are all already documented in the schema with their provenance and formats. The description adds no meaning about the raw flag's effect on returned shape or about the pagination contract, 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 specific verb ('Read') and a precisely scoped resource ('your own submission'), then enumerates the returned content: prior attempts, teacher comments, rubric feedback and saved what-if score. That enumeration plus the 'your own' scope distinguishes it from list-oriented siblings like canvas_course_submissions.

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?

The closing 'Does not mark feedback read' implies the read-state boundary, but no alternative tool is named for the case where the caller wants to mark feedback read or view another student's submission. Usage context is implied rather than stated as 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.