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

Annotations already indicate destructive and non-idempotent behavior, but the description adds crucial caveats: 'Does not reverse work the host already did,' scope restriction, and the approval workflow. This meaningfully extends what structured annotations convey, even though it doesn't detail all possible side effects.

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 core sentence is concise and front-loaded with purpose and usage. The bracketed approval guidance is additional but relevant; the description is efficient without being bloated.

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 single-required-parameter cancel tool, it explains the object, side effects, scope, and approval flow. It lacks return/error handling details, but no output schema exists and those are not essential for correct invocation.

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 schema already documents both parameters. The description adds little beyond 'pending' and scope; the mention of 'target_session_id' could be slightly confusing since the parameter is named 'id'. Baseline 3 is appropriate.

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?

Clearly states a specific verb and resource: cancel a pending attention directive, with explicit reasons (operator changed mind / wrong target). It distinguishes from siblings like create_attention_directive and ack_attention_directive by emphasizing cancellation of pending directives and scoping to 'THIS operator only.'

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?

Provides explicit trigger scenarios: operator says drop/cancel that instruction to Grok or Claude, or CoS realizes the target_session_id was wrong. It also includes operational guidance about write-tier approval and not re-asking in chat. However, it doesn't name sibling alternatives directly, so it's not a perfect 5.

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