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

Goes well beyond the annotations by disclosing the authorization model: the handle must be server-issued and the human must approve in AIMixer, and it explicitly rules out tool calls, host text, OAuth grants or 'approved=true' as spend consent — valuable anti-prompt-injection context for a destructive, non-idempotent tool. It stops short of describing the operational effect, e.g. that spend is incurred, how long the execution runs, or what a repeat call does given idempotentHint=false.

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, zero waste, with the hard precondition front-loaded before the prohibition clause. Every sentence earns its place.

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 destructive, non-idempotent mutation with no output schema and no parameter documentation, the definition leaves out what the agent should do after starting (e.g. poll aimixer_canvas_get_execution), what happens on repeated invocation, and what identifies the started execution. The safety contract is strong; the operational picture is thin.

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 0%, so the description must compensate, and it only does so for approval_handle (server-issued, human approval, exact match). project_id and request_id are left entirely to their type/pattern constraints with no explanation of where they come from or how they relate to the prepare step.

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?

Names a specific verb and resource ('Start a previously prepared Canvas request') and ties it to a precondition artifact (the approval_handle). It implicitly routes away from the prepare/get/stop siblings, but never names them, so an agent must infer that aimixer_canvas_prepare_execution is the prerequisite.

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?

States a clear precondition: the request must already be prepared and the human must have approved it in AIMixer. It does not name alternative tools (aimixer_canvas_prepare_execution, aimixer_approval_status, aimixer_canvas_get_execution), nor does it say what to do when the handle is missing or stale.

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