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

The phrase 'Values discarded' is a useful behavioral disclosure beyond the basic operation. With no annotations provided, the description carries the full burden, but it does not describe error behavior, return shape, or whether nested objects are traversed, so transparency is only partial.

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 short, front-loaded sentences with no filler. Both sentences earn their place: one states the operation, the other states the key behavioral constraint.

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?

Despite being a simple-sounding tool, the input schema is noisy with nine optional string parameters and no output schema. The description does not explain which parameter carries the JSON object, whether the JSON should be passed as a string, or what the count result looks like, leaving an agent likely to misinvoke the tool.

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%, which normally earns a baseline 3, but none of the nine string parameters is clearly identified as the JSON object whose keys are counted. The 'json' parameter says 'JSON text to validate', not 'JSON object to count', so the description adds no help in mapping the tool's purpose to its actual inputs.

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 clear verb and resource: count keys in a JSON object, with values discarded. This semantically distinguishes it from sibling tools like validate-json. However, it leaves ambiguity about whether 'keys' means top-level or nested keys, and which schema parameter actually supplies the JSON object.

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?

There is no guidance on when to prefer this tool over alternatives such as validate-json or search-query-len. The description neither states a clear use case nor warns against using it when values or validation are needed.

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