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

Without annotations, the description carries a heavier burden, and 'Query discarded' does disclose the key privacy-relevant behavior that input is not retained. However, it does not describe the return value format, edge-case handling, or how non-query fields are treated, leaving meaningful behavioral gaps.

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 two short sentences with the core operation front-loaded and no wasted words. 'Query discarded' earns its place as a meaningful behavioral note. This is an appropriately sized definition for a simple utility.

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 no annotations and no output schema, the description covers the basic operation and data handling, but it omits the return format and leaves the large optional-parameter schema unexplained. An agent could likely invoke it via 'query', but might hesitate given the many unrelated fields.

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 already gives every parameter a description, and the 'query' property clearly maps to the described search query. The description adds the role of the query as the value being counted, but it does not clarify whether the many other optional properties are ignored or how an agent should choose among them.

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') and a specific resource ('a search query'), with 'characters' clarifying the unit being measured. It is not perfectly differentiated from siblings, but it is clear and not merely a tautology because it adds the character-count and discard details.

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?

The description gives no guidance about when to use this tool versus sibling tools such as validate-json, normalize-url, or the various shape-checking tools. 'Query discarded' hints that it is a lightweight stateless utility, but no explicit usage context or exclusions are provided.

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