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

No annotations are present, so the description carries the full burden of behavioral disclosure. It does disclose a meaningful behavior: values are discarded, not returned. However, it does not mention whether invalid JSON is handled, whether keys are counted recursively or only at the top level, or what output the tool returns.

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 two short sentences with no filler. The core action ('Count keys') is front-loaded, and the note about values being discarded is concise and relevant.

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 nine parameters, no output schema, and no annotations, the description is under-specified. It does not explain the return value, counting scope, error behavior, or how the various input parameters relate to the JSON object. An agent would struggle to confidently invoke this 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?

The input schema has 100% coverage, so the baseline is 3. The description adds no parameter-level meaning beyond the schema. It does not specify which parameter holds the JSON object to count, though the schema's 'json' field description partially covers this.

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 verb and resource: 'Count keys in a JSON object.' The added 'Values discarded' helps set expectations and distinguishes it from value-returning tools. However, it does not explicitly differentiate it from sibling tools or clarify whether the JSON object is the input object itself or the value of the 'json' parameter.

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?

No guidance is provided about when to use this tool versus alternatives like validate-json or search-query-len. The description states what the tool does but gives no conditions, exclusions, or context for choosing it.

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