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

No annotations are provided, so the description carries the full behavioral burden; it does meaningfully disclose that all values are discarded, reinforced by per-parameter notes like 'discarded after the shape check' and 'titles discarded.' This honestly signals that none of the tempting parameter names trigger real fetches, normalization, or validation side effects. However, it never states the return format, whether the operation is strictly read-only, or whether any external call could occur, leaving the disclosure 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 sentences with zero filler: the verb and object are front-loaded, and the second sentence carries the single most important caveat. Every word earns its place, and nothing could be cut without losing meaning.

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?

For a low-complexity tool, the core function is stated clearly and the schema fully documents all parameters, so the description is not cripplingly incomplete. But there is no output schema and no annotations, and the description never states the return value or format, does not resolve which JSON object is being counted, and does not address behavior when called with zero of the 9 optional parameters. These are real but moderate gaps for a tool whose entire output is a single number.

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%, so every one of the 9 parameters is already documented in the schema, setting the baseline at 3. The description adds a mild unifying frame — that all inputs are merely keys to be counted and values to be discarded — which helps the agent avoid expecting per-parameter behavior. It does not clarify how missing versus provided keys affect the count or how the params map onto the object being counted.

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 and resource ('Count keys in a JSON object') plus the value-discard policy, so it is not a tautology. However, the input schema exposes nine unrelated string parameters and no object-typed parameter, leaving ambiguous whether the counted object is the whole input object or a JSON string value. It also does nothing to differentiate the tool from counting/validation siblings such as validate-json, hn-front-count, or search-query-len.

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 when-to-use or when-not-to-use guidance, and no alternative or exclusion is named. With 27 siblings spanning validation, URL normalization, weather, and counting tools, the agent is left to infer routing entirely from the name and the terse purpose sentence. The only implied signal is that this tool counts keys and ignores values, so it is not the tool for real normalization or validation work.

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