Discard Control Build

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

With no annotations, the description carries the full burden and does so richly: it discloses what is destroyed (staged items), what is preserved (published controls untouched), side effects (model released, build re-proposed), cost (credits not returned), and a hard precondition (pause a running build first).

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?

Front-loaded with the verb+resource and the mutating flag, then behavior, then return shapes. Every sentence is informative, though the enumerated return block is somewhat verbose given an output schema already exists.

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 mutating tool with zero annotations, the description covers destruction semantics, side effects, credit cost, and preconditions, plus concrete success/error return codes. An agent has everything needed to call it correctly without opening the schema.

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%: model_id is documented in the schema, server_version is not. The description adds no parameter-level meaning beyond the schema (it only refers to 'a model'), so it neither compensates for the coverage gap nor adds value. Baseline 3 for a two-param tool where the schema does the documented half.

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 ('discard') and resource ('a model's held control build') and immediately qualifies the operation as mutating. It clearly separates itself from siblings like delete_control and start_control_build by scoping to a held (non-running) build.

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?

Explicitly enumerates the applicable states (queued, deferred, paused, blocked) and the exclusion condition: a running build must be paused first, naming the alternative tool (pause_control_generation) and the wait condition. This is explicit when/when-not guidance with a named alternative.

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