derive_criteria

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

Annotations already indicate a write operation that is not destructive. The description adds that it asks the host model and persists only a draft, which is useful side-effect context. It does not go deeper into what exactly is persisted or whether anything existing is overwritten, but it does not contradict the annotations.

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 with no filler. Every word contributes to the core action and constraint.

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 has a simple single-parameter schema and an output schema, so the description does not need to explain return values. Still, the meaning of 'host model' and 'observable criteria' is not defined, and the relationship to set_criteria is only implicit, leaving moderate contextual gaps.

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% and the only parameter, task_id, is already documented as 'Identifier returned by create_task.' The description adds no additional meaning about the parameter, so the baseline of 3 is appropriate.

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 a specific action ('derive') and target ('observable criteria') and clarifies that only a draft proposal is persisted. This distinguishes it from a sibling like set_criteria, though 'host model' and 'observable criteria' are left somewhat unexplained.

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 phrase 'persist only a draft proposal' implies this tool is for producing a preliminary draft rather than final criteria, which hints at the relationship to set_criteria. However, there is no explicit statement of when to use this tool versus other siblings or what workflow position it occupies.

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