canvas_get_submission

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

The description adds behavioral context beyond the annotations: it explicitly states all requests use Canvas GET endpoints and that the server cannot modify Canvas. It also discloses the scope ('current user'), which is not present in the readOnlyHint annotation. While the annotations already cover the read-only safety profile, the description reinforces and adds user-scoping details.

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 description is three short sentences, each serving a distinct purpose: establishing read-only access, reinforcing GET usage, and specifying the exact data returned. There is no unnecessary verbiage, and the most important information is front-loaded. This is highly concise and well-structured.

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?

The tool lacks an output schema and has only basic parameter names. The description lists the return components (submission, comments, rubric assessment) but does not explain the response structure, potential error conditions, or whether the submission might be absent. For a simple read-only tool, this is adequate but leaves room for ambiguity. Sibling differentiation is present but not exhaustive.

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?

The schema description coverage is 0%, so the description must compensate for the absence of parameter documentation. However, the description does not mention course_id or assignment_id at all, nor does it explain their meaning, constraints, or how they relate to the current user's submission. The parameter names are self-explanatory, but the description adds minimal semantic value beyond the schema structure.

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?

The description clearly states the tool's function: 'Read the current user's submission, comments, and rubric assessment.' It uses a specific verb ('read') and identifies the resource ('submission') and distinguishes itself from siblings by specifying the current user and the included components. The read-only nature is also explicit, separating it from any modifying tools.

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 description provides clear context: it is read-only and uses GET endpoints, so it is safe to use. It implicitly indicates when to use it (when needing the current user's submission for a course/assignment) but does not explicitly mention alternatives or exclusions. This aligns with 'clear context, no exclusions'.

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