Remove a step from a purchase-requisition

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

Annotations already flag destructiveHint=true; the description adds that the purchase-requisition version is bumped and that active runs retain their step, so previously ticked data is not rewritten. This goes beyond the annotation in a meaningful way.

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 compact sentences front-load the core action and then add the one consequential caveat. No filler or repetition of schema details.

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 two-parameter destructive mutation with no output schema, the description provides the action, identifier format, side effects, and a safety guarantee about in-flight runs. It is enough to call correctly, though return behavior is not described.

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?

Both parameters are fully documented in the schema, including examples (I03, CL-0001). The description echoes the I01-style identifier but adds no new parameter-level semantics, so the schema carries the 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 ('Remove'), a precise resource ('one step from a purchase-requisition'), the identifier style ('I01-style id'), and the side effect (version bump). This clearly distinguishes it from sibling tools like purchase-requisition_item_add.

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 implies the use case—removing a step—but does not explicitly state when to prefer this over purchase-requisition_item_add or mention exclusions. The note about runs is behavioral context, not usage guidance.

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