wave_design_contract_check

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

There are no annotations, so the description carries the full burden. 'Validate' suggests a read-only check, and 'no compose' is a useful behavioral disclosure that prevents the agent from expecting composition side effects. Still, the description does not disclose what happens on validation failure, whether the tool returns a structured report, or whether any state is modified, leaving notable behavioral gaps.

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 states the core action, target resource, and validation criteria without any filler. Every word earns its place, and the 'no compose' caveat is packed in efficiently. This is an ideal length for a simple one-parameter validation tool.

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 tool with one parameter and low complexity, the description says enough to select and invoke it, but it omits return behavior entirely. Since there is no output schema, the agent cannot know whether the tool reports success/failure, outputs a detailed report, or throws an exception. The absence of this information is a real gap for a validation tool, though the tool is otherwise simple.

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 100%, so the baseline is 3. The description adds little beyond the schema: it says the file must be 'existing', which slightly clarifies permissibility, and hints at the kind of file (design-contract.json), but it does not elaborate on path format, validation behavior, or output. The parameter semantics remain essentially as documented in the schema.

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 specific verb 'Validate' against a clearly identified resource ('existing design-contract.json') and names the acceptance-tests catalogue and schema as validation criteria. The 'no compose' clause helps differentiate it from a possible create/compose workflow. This is unambiguous and distinguishes the tool from likely siblings.

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 'existing design-contract.json' implies it should be used for pre-existing contracts rather than creating new ones, and 'no compose' tells the agent this tool will not run a compose step. However, it does not explicitly name any alternative sibling or state when to choose this tool over wave_design_contract, wave_design_extract, or wave_design_measure. Usage is implied, not spelled out.

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