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

With no annotations provided, the description carries the behavioral disclosure burden. It clearly discloses a non-obvious behavior: values are discarded, meaning the result depends only on key presence. It does not spell out the return type, but 'Count' strongly implies a numeric count and the operation is inherently read-only.

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 sentences, no filler, and the key behavior ('Values discarded') is front-loaded immediately after the purpose. Every word earns its place.

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 is mostly sufficient for a simple counting tool, but it leaves some ambiguity about whether 'a JSON object' refers to the tool-call arguments object or a JSON payload to inspect, especially given the 'json' parameter. There is no output schema, and the description does not explicitly state the return value, though 'Count' implies it.

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 coverage is 100%, so baseline is 3. The description adds important meaning by stating that values are discarded, which clarifies that the content of the string parameters does not matter beyond satisfying the schema. This prevents misusing the parameter descriptions as value-dependent instructions.

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 uses a specific verb ('Count') and resource ('keys in a JSON object'), and the additional 'Values discarded' disambiguates it from related validation and shape-check tools. It clearly distinguishes from siblings like validate-json, which validates rather than counts.

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?

Usage is implied by the description: use the tool when you need to count keys and ignore values. However, it does not explicitly state when to prefer it over alternatives or call out exclusions, so the guidance is implicit rather than explicit.

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