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

Annotations only declare destructiveHint=true, and the description adds substantial value on top: it warns this STOPS IN-FLIGHT WORK across production functions, advises tight scoping, and clarifies that completed runs are untouched. It still omits whether the action is reversible/what the delete sibling does with the result, so it falls short of the fullest disclosure.

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 short sentences, the destructive scope stated up front with capitalization for emphasis, then the boundary condition, then the API endpoint. Every sentence earns its place with no 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?

The tool is well covered for a destructive bulk operation with no output schema, and the endpoint hint is useful. What is missing is any hint about what comes back (e.g. a cancellation identifier that the sibling inngest_delete_cancellation would consume), which an agent would want when deciding whether to chain calls.

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 description coverage is 100%, so every parameter including the CEL 'if' filter is already documented in the schema; the description only restates the time window and event-expression narrowing at a high level. Baseline 3 is appropriate when the schema carries the semantic load.

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 and resource (cancel every run of one function), plus the scoping dimensions (time window, event expression). The verb/scope combination clearly separates it from the sibling list/delete cancellation tools, so an agent can select it without opening the schema.

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?

Gives clear context for when the tool applies (in-flight runs inside a window) and an explicit warning to narrow the window tightly, plus the important boundary that already-finished runs are unaffected. It does not, however, name the alternative tools (e.g. inngest_list_cancellations to preview, or inngest_delete_cancellation to undo), so exclusions and alternatives are left implicit.

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