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

Annotations provide only basic hints (readOnly=false, idempotent=false, destructive=false), so the description carries the burden of behavioral disclosure. It clarifies that repair output is suggested values rather than applied changes, but it does not state whether the call has side effects, requires special authorization beyond api_key, or how the repair suggestions are generated. The phrase 'include repair suggestions... in the same call' is informative but not comprehensive.

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 sentences, each earning its place. The primary action, the conditional repair behavior, and the compatibility with 'validate' verdicts are all front-loaded in a compact, readable way with no filler.

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?

Given no output schema, the description does a good job of indicating what the response will include (PASS/FAIL/REVIEW, reasons, proof, and repair suggestions). The main gap is that it doesn't explicitly clarify whether the operation is read-only or whether repair suggestions are always returned or only on FAIL, but the phrase 'when it fails' implies the latter. For a 3-parameter tool, this is nearly complete.

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 baseline is 3. The description adds meaning beyond the schema by explaining the relationship between structured_data, Blueprint rules, and the repair suggestions (corrected values with the rule each fix is based on). This helps an agent understand how the parameters interact, which is more than simple schema restatement.

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 states a specific verb ('Validate'), the resource ('structured data against a Blueprint'), and the key distinguishing feature ('when it fails, include repair suggestions (corrected values with the rule each fix is based on) in the same call'). It also references the sibling 'validate' tool by saying 'Same verdicts as validate', making the scope and differentiation clear.

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 clearly implies this tool is for cases where you want validation and repair suggestions in a single call rather than a separate validate-then-repair flow. However, it does not explicitly state when to prefer plain 'validate' or the standalone 'repair' sibling, leaving some routing to inference.

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