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

With no annotations, the description carries the full burden of explaining side effects. It mentions 'Values discarded' but does not explicitly state that the operation is read-only or free of side effects. The read-only nature is implied but not confirmed.

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, pithy sentence that immediately conveys the core action. It is well-structured and avoids unnecessary detail, though slightly more context would improve usability.

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?

The description fails to specify which parameter contains the JSON object, what constitutes a 'key' (nested keys vs top-level), or what the output format is. This lack of essential context makes the tool difficult to use 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 schema descriptions for parameters (e.g., 'Git ref name; discarded after the shape check') are generic and misleading. They do not clarify that only 'json' is relevant for counting keys, leaving an agent confused about which parameters to provide.

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 the tool's primary function: counting keys in a JSON object. However, the presence of nine unrelated parameters in the schema creates ambiguity about which input actually represents the JSON, preventing a perfect score.

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 on when to use this tool instead of alternatives like validate-json or file-path-ok. The description does not mention any specific use case or comparison with sibling tools.

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