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

With no annotations, the description must carry the full behavioral burden. It only mentions counting keys and discarding values, but does not disclose whether the tool makes external calls, requires permissions, or has side effects. The schema descriptions for parameters like 'url', 'city', and 'feed' suggest additional behaviors that are unexplained, creating confusion about what the tool actually does.

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, efficient sentence that front-loads the core action. It avoids fluff and is appropriately short. However, brevity comes at the cost of necessary detail, making it slightly under-specified rather than purely 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 parameters, no required fields, and no output schema, the description is grossly incomplete. It does not state which parameter is the JSON input, what the return value looks like, or how the tool behaves with multiple parameters. An agent would have no idea how to correctly invoke this tool for counting keys.

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 schema coverage is 100%, the parameter descriptions conflict with the stated purpose. For example, 'json' is described as 'JSON text to validate', not as input for key counting. The description does not clarify which parameter is the JSON object or how the other eight parameters relate to the operation. It fails to add meaningful linkage between the tool's purpose and its schema.

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 specific action ('Count keys in a JSON object') and notes that values are discarded. This is clear enough to distinguish it from sibling shape-checkers like domain-shape or validate-json. However, it does not specify how the JSON object is provided, leaving ambiguity about which parameter holds the input.

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 given on when to use this tool versus alternatives. It does not mention contexts, exclusions, or comparisons to siblings like validate-json or search-query-len. The description offers no selection criteria.

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