Refine project

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

Even though destructiveHint=true is annotated, the description adds substantive consequences beyond it: accepted/rejected fixes may be replaced, clips re-render afterwards, and vocabulary can be cleared with an empty string. It also discloses the return shape ({ ok, steps }), which the tool has no output schema for.

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?

Dense but front-loaded: the core action and its variants come first, then side effects, then the return value and follow-up. No sentence is filler, and semicolon-separated clauses keep it compact.

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 three-parameter mutation with no output schema, the description covers the step semantics, vocabulary lifecycle, destructive consequences, re-render side effect, return shape, and the correct follow-up call. An agent has everything needed to invoke it correctly.

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%, so the schema already documents id, steps and vocabulary. The description adds only marginal meaning, notably the comma-separated format for vocabulary and the default-all behavior for steps, both of which the schema largely covers already.

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 (re-run) and resource (refine steps on the existing transcript), and enumerates the three step types with parenthetical clarification of what each does. It does not distinguish itself from close siblings like reanalyze_project or retry_project, which is the only gap.

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?

Gives clear operating context: steps default to all three when omitted, and vocabulary can optionally be set 'first'. It also routes the agent's next action ('then wait_for_project'), but never states when to prefer this over reanalyze_project or retry_project.

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