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

Without annotations, the description must disclose behavior itself; 'Query discarded' is a useful privacy signal, but it does not describe return format, whether a missing query yields an error, or how character counting is defined. The description's mismatch with the schema further obscures the runtime behavior.

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 text is very short and front-loads the action, so there is no waste. However, it is so terse that necessary information (which parameter is the query, what counts as a character) is missing, making it under-specification rather than efficient specification.

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 tool with seven parameters and no output schema or annotations, the description leaves no explanation of how to form a valid call or what result to expect. The single meaningful guarantee is that the input is discarded, which is insufficient for an agent to use the tool.

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 the input schema has high per-property description coverage, the description refers to a 'search query' that does not map to any of the seven properties (ref, url, city, feed, host, json, path). The description therefore adds no usable parameter semantics and actually makes invocation ambiguous.

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 characters in a search query') but the input schema contains no `query` property, so the tool's purpose cannot be tied to a callable parameter. It essentially restates the tool name and does not distinguish itself from sibling counting tools like hn-front-count or memory-key-count.

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 about when to choose this tool or avoid alternatives, and there is no parameter named `query`, so an agent cannot infer which input supplies the value to count. The phrase 'Query discarded' addresses post-call handling, not tool selection.

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