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

Annotations provide readOnlyHint=false and destructiveHint=false, which already signal mutation and potential impact. The description adds valuable behavioral context: cancellation is not immediate (next campaign boundary), already-pushed campaigns are not rolled back, and it's scoped to the active Space. This goes beyond annotations but could mention what happens to the sync status or if cancellation can fail, so a 4 is appropriate.

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?

Two sentences, front-loaded with the primary action, followed by critical behavioral notes and scoping clarification. Every sentence earns its place—no filler or redundancy.

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 the tool's complexity (mutation with scoping behavior), the description covers the key aspects: how cancellation works, what it does not do (rollback), and how Space scoping is handled. It lacks an explicit return value description, but there is no output schema and the sync status can be verified via get_sync_status, so the description is largely complete. A 4 rather than 5 because it doesn't mention prerequisites like having a sync actively running or any error conditions.

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 50%: sync_id has no description in the schema, but the description clarifies that it targets a running sync. space_id has a detailed schema description, and the tool description reinforces how it overrides the active Space. The description adds meaning for sync_id beyond the schema, so it compensates for the coverage gap.

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 verb ('Request cancellation') and resource ('a running sync'), and distinguishes this from sibling tools like trigger_sync and get_sync_status. It also specifies the cancellation is scoped to the active Space, which differentiates it from other sync-related operations.

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 explicitly explains when to use this tool versus alternatives: it mentions canceling a running sync, that it takes effect at the next campaign boundary, and that it's scoped to the active Space with a note to use set_active_space to switch or pass space_id to override. This provides clear context and exclusions.

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