cancel_operating_loop

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

Annotations already disclose that this is destructive (destructiveHint: true), not read-only, and idempotent. The description adds an eligibility restriction, but it does not explain side effects, reversibility, state requirements, or consequences of cancellation. Given the annotations carry the core safety profile, the description adds only marginal behavioral context, earning a 3.

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 description is a single front-loaded sentence that begins with the action 'Cancel'. It is appropriately brief and contains no filler. However, the cryptic middle clause reduces the clarity of the sentence, so it does not reach a 5.

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 operation with five required identifiers and a delicate eligibility condition, a single cryptic sentence is insufficient. The description does not explain what 'hidden source custody' means, what state the loop must be in, how to obtain loop_ref/run_ref, or what happens after cancellation. The presence of an output schema reduces the need to describe return values, but the operational context is still largely missing.

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 0%, and the description provides no information about any of the five required parameters (company_ref, project_ref, loop_ref, run_ref, reason). The property names are somewhat self-explanatory, but the description does not compensate for the lack of schema-level parameter documentation as required when coverage is this low.

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 uses the verb 'Cancel' and identifies the resource as 'loops', so the basic action is clear. However, the qualifying phrase 'whose public authority needs no hidden source custody' is opaque domain jargon that does not explain what an operating loop is or what cancellation entails. It is neither a tautology nor fully specific enough to be a 4 or 5.

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 'only' provides an implied eligibility condition: cancel loops meeting a certain criterion. However, the description does not name alternatives, state when not to use the tool, or contrast with sibling lifecycle tools such as get_operating_loop_status or start_operating_loop. The guidance is present but mostly implicit and obscured by undefined terminology.

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