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

Annotations already declare destructiveHint=true and idempotentHint=false. The description adds critical context beyond that: the terminal consequence 'a mid-flight cancellation can leave the affected resource between versions until the next reconcile' is a genuinely useful behavioral disclosure not captured by annotations. It also clarifies idempotency-adjacent behavior: 'Not running executions answer their settled state unchanged.'

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 tightly-packed sentences: purpose with resource definition, usage caution with rationale, and non-running behavior. No filler; the caution is front-loaded appropriately for a destructive tool.

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 single-parameter tool with annotations covering safety flags, the description supplies the missing pieces: consequence of mid-flight cancellation, preference ordering vs alternative, and no-op behavior. Nothing an agent needs to decide to call this is absent.

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 100%, so the single parameter is fully documented. The description adds value by referencing list_recent_executions as the source for execution_id, reinforcing correct lookup flow beyond the schema's own description of the field.

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?

States a specific verb+resource ('Cancel a running platform execution') and defines the resource by enumerating what an execution is ('a deploy, sync, or other operation from list_recent_executions'). This distinguishes it from siblings like cancel_agent_run, cancel_data_run, and cancel_execution_step which cancel different resources.

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 discourages use: 'prefer letting a deploy finish and rolling back unless it is actively harmful.' It names an alternative behavior (wait + rollback) and gives the condition under which cancellation is warranted, plus notes behavior for non-running executions.

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