cancel

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

The description candidly discloses that cancellation is best-effort with the agent possibly finishing anyway, that force: true kills the agent process, and that returning not-running vs not-found maps to resumable vs unknown sessions. This goes well beyond the annotations' destructiveHint and idempotentHint, offering essential side-effect and error semantics. No contradiction.

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 a single dense paragraph with the main purpose front-loaded. Every sentence contributes a distinct behavioral nuance—best-effort nature, cancellation protocol, return flag, serialized-host limitation, force semantics, and status results—without repeating schema or annotations. 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 there is no output schema and annotations are limited, the description fully explains return values, edge cases, and behavioral constraints. It covers cancellationRequested flag, not-running (resumable) and not-found states, serialized-host caveat, and force kill behavior, leaving little ambiguity.

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 documents force but gives no description for sessionId. The description adds meaning by clarifying that sessionId identifies the in-flight delegation and by explaining the status outcomes associated with it. It also reiterates the force behavior from the schema, providing value on top of 50% schema coverage.

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 opens with 'Best-effort cancel of an in-flight ACP delegation by sessionId,' providing a specific verb (cancel), resource (in-flight delegation), and key parameter (sessionId). It clearly distinguishes from siblings by focusing on cancellation, while delegate starts and doctor diagnoses.

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 identifies the clear use case of cancelling an in-flight delegation and includes a when-not limitation: MCP hosts that serialize tool calls cannot run this while delegate is in flight. However, it does not explicitly name alternatives like 'use delegate to start a delegation' or contrast with doctor, so it stops short of full 5.

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