canvas_cancel_action

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

Beyond the annotations, it discloses that the discard is local-only and never contacts a Canvas write endpoint, and that already-executing actions are out of scope. It does not say whether a discarded action is recoverable or idempotent, which would complete the picture for a state-changing 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 short sentences with zero filler; the primary action is front-loaded and the negative constraints follow immediately after. Nothing is repeated from schema or annotations.

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?

An output schema exists, so return values need no explanation, and the annotations cover the safety profile. However, for a state-changing tool the definition leaves open the id's provenance and post-cancel state of the discarded action, which an agent still needs in order to call it safely.

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 0% for the single required action_id, so the description must carry the semantics. It only indirectly conveys that the id refers to a previously prepared action, without saying where the id comes from (prepare/status tools) or what happens with an unknown or stale id.

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?

Uses a specific verb and resource ('Discard a prepared action') and implicitly separates itself from canvas_prepare_* (create), canvas_execute_action (run), and canvas_action_status (inspect). An agent can tell what this tool does and does not do without opening any schema.

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 a clear trigger condition ('if the user declines or no longer wants it') and an explicit exclusion ('an executing action cannot be cancelled here'), plus a redirect to inspect the receipt and Canvas state. It stops short of naming the sibling tools that provide those alternatives, but the routing intent is unambiguous.

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