Canvas API Request

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

Beyond annotations (destructiveHint=true, readOnlyHint=false), the description adds crucial behavior: writes happen 'immediately' and 'cannot be undone from here', plus the note that permission is governed by Canvas role. It also explains the dry_run feature as a safety preview, all of which enriches the agent's understanding of side effects.

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?

Four sentences, each earning its place: purpose, warning, endpoint-lookup instruction, and dry_run tip. Front-loaded with the primary purpose, followed by critical safety information. No fluff.

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?

Given the tool is a raw API executor with an output schema (so return values need not be explained), the description fully covers the necessary context: what it does, when to use it, what risks exist, how to preview safely, and that permissions are role-based. It is complete for an agent to select and invoke correctly.

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 covers all parameters, so baseline is 3. The description adds value by explaining dry_run's purpose ('preview the prepared request without sending it') and by linking method semantics to destructive actions ('Non-GET methods CREATE, MODIFY, or DELETE'). This goes beyond the plain parameter descriptions.

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 'Executes any Canvas API endpoint directly' with a specific verb and resource, and distinguishes itself from sibling tools by framing it as the direct API access route. It also tells users to 'Find endpoints with search_canvas_api first', further differentiating it from that discovery tool.

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 warns that non-GET methods have irreversible effects, which serves as a strong 'when not to use' signal for casual exploration. It also instructs to use search_canvas_api first to discover endpoints, creating a clear usage workflow. Mentions dry_run=true as a safe preview option.

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