Raw Canvas Request

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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds the operational gates the agent cannot see otherwise: an environment flag that can disable all writes, a mandatory confirm flag, and a hard refusal on quiz-submission writes. That is exactly the beyond-annotation context that prevents a failed or rejected call.

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, zero filler, with the tool's role stated first and the write-safety constraints immediately after. Every clause carries either routing or safety information.

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 an open-world passthrough with seven parameters and no output schema, the description covers invocation and safety well. The remaining gap is that it never characterizes the response (raw JSON envelope, error shape, pagination behavior beyond the schema's paginate flag), which matters for a tool that can hit arbitrary endpoints.

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 baseline is 3, but the description adds meaning the schema cannot: that confirm is tied to a write-enablement flag rather than being a bare boolean, and that method choice carries read-vs-write consequences. It does not explain path/params composition, which the schema handles adequately.

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 ('Call any Canvas REST API endpoint directly') and defines its role as the escape hatch for 'anything the other tools don't cover', which distinguishes it from every sibling in the list without naming one. An agent immediately understands this is the generic fallback rather than a scoped operation.

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?

Gives an explicit use condition (when no specialized tool covers the need) and precise when-not/gating rules: writes are blocked when CANVAS_ALLOW_WRITES=false, require confirm=true, and quiz-submission writes are always refused. It also splits guidance by method, telling the agent GET is safe while the other three mutate.

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