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

Annotations already provide read-only, idempotent, non-destructive hints. The description adds valuable context beyond annotations: deterministic JSON Pointers, explicit error truncation, input hashes, and no remote reference resolution. These details align with and enrich the annotation profile, making the tool's behavior transparent.

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 dense sentence that front-loads the core purpose and then lists specific behaviors. It is informative without excessive verbosity, though it could be slightly more structured (e.g., splitting into two sentences) to improve readability. Every clause contributes value, so it earns a high score.

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 the tool's moderate complexity (4 params, output schema present, nested objects), the description covers essential aspects: purpose, constraints (bounded, no remote refs), and return characteristics (pointers, truncation, hashes). The presence of an output schema relieves the description from detailing return types, and it provides enough context for an AI agent to use the tool 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?

With high schema description coverage (75%), the baseline is 3. The description does not add parameter-specific meaning; it focuses on overall behavior. The schema already describes `schema` and `check_formats` well, but `instance` and `max_errors` rely on types and defaults, which the description does not elaborate on. It neither compensates for gaps nor adds extra insight.

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 clearly states a specific action ('Validate') with a well-defined resource ('JSON data') and scope ('bounded JSON Schema Draft 2020-12 contract'), and it enumerates supported keywords. It differentiates from sibling tools like data.schema by focusing on validation rather than schema definition or other data operations.

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 implies when to use it (validating JSON against a schema) and hints at limitations ('bounded', 'no remote reference resolution'), but it does not explicitly mention alternative tools or when not to use it. The guidance is primarily inferable from the capabilities listed rather than direct comparison with siblings.

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