create_cancellation

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

No annotations are provided, so the description carries the full behavioral burden for a destructive bulk operation. It never says whether cancellations are reversible, whether already-completed runs are affected, whether there is a cap on matched runs, or that this is irreversible and should be used with care.

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 short sentences, front-loaded with the bulk scope and followed by the concrete mechanics. There is mild redundancy between 'matching criteria' and the filter clause, but nothing wasteful.

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?

A destructive mutation tool with no annotations and no output schema needs to disclose blast radius and reversibility; the description says nothing about the number of runs affected, whether the action can be undone, or what is returned. The agent cannot judge the risk of calling it from this text alone.

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% with per-parameter descriptions including ISO 8601 formats and the CEL expression type, so the schema does the heavy lifting. The description restates the time range and optional filter but adds no syntax or constraint detail beyond the schema (e.g., valid CEL fields or inclusive/exclusive bounds).

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 (cancel) and resource (all runs of a function) plus the scoping mechanism (time range + optional expression filter), which separates it from the singular cancel_run sibling. It stops short of naming cancel_run explicitly, so the differentiation is inferable rather than stated.

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 word 'Bulk' plus the matching-criteria framing implies this is for cancelling many runs at once rather than a single run, but the description never states when to prefer this over cancel_run or list_cancellations, nor any prerequisites. Usage is only implied.

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