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

The annotations already declare destructiveHint=true, but the description adds meaningful detail beyond that: 'destructive: kills active Axint child process groups; no network.' It explains the exact destructive effect and the scope (child process groups). This provides valuable context beyond the structured annotations, though it could have stated more about process escalation details.

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 relatively concise but includes some redundancy and awkward repetition of 'Use'. It front-loads the core purpose but then has a slightly disjointed structure with the parameter section that doesn't align with the schema. Still, it conveys a lot of important information in a compact form.

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?

The description covers the main scenarios, effects, and scope of the tool, and the presence of an output schema reduces the need to explain return values. However, the contradictory parameter information creates a significant gap in understanding how to actually invoke the tool. For a destructive tool with no required parameters, this mismatch is a notable completeness issue.

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 description is misleading regarding parameters. It states 'Inputs: jobId is required; signal and grace period control escalation before killing the process group.' However, the actual schema contains parameters `id`, `cwd`, and `format`, none of which are required. The description introduces non-existent parameters (jobId, signal, grace period) and incorrectly claims requiredness. Even though schema description coverage is 100%, the description actively contradicts the schema and adds confusion, so it receives the lowest score.

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 the action: 'Cancel the latest or selected Axint run by killing active child process groups.' It specifies the resource (Axint run) and the method (killing child process groups), which distinguishes it from other tools. The sibling comparison shows it is obviously different from read-only tools like run.status.

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?

Explicit usage guidance is given: 'Use this when xcodebuild or a UI-test runner survived an MCP timeout or transport close.' It also states exclusions ('use only to stop an active run or stuck child process group') and names an alternative tool ('use run.status for read-only inspection'). This is excellent context for when to select this tool.

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