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

The description notes that values are discarded, hinting at read-only behavior, but does not disclose side effects, error behavior, output format, or any constraints. With no annotations provided, the description carries the full burden of transparency and falls short.

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 succinct and free of unnecessary words, using clear, direct sentences. It could benefit from a brief example, but overall it is well-structured and concise.

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?

With nine optional, seemingly unrelated parameters and no output schema, the description leaves the agent without enough context to confidently invoke the tool. It fails to explain which parameter is the actual input, what the return value looks like, or how to handle the irrelevant fields.

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?

Although the schema has 100% description coverage, the parameter descriptions are inconsistent with the tool's stated purpose. For example, `json` is described as 'JSON text to validate' and `query` as 'discarded after the length check', neither matching key counting. There is no parameter that clearly represents the JSON object whose keys are to be counted.

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—counting keys in a JSON object and discarding values—which distinguishes it from validation or search tools. However, the input schema does not include an obvious JSON object parameter, and the `json` param is described as validation, creating ambiguity about what the tool actually operates on.

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 provides no guidance on when to use this tool versus alternatives like validate-json or search-query-len. There is no mention of appropriate contexts, limitations, or selection criteria.

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