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

Annotations include openWorldHint:true, indicating the tool's response may not be exhaustive. The description adds that it counts enterprises with external investments in the last two years and excludes lists and other categories, but does not disclose potential limitations like data lag or partial coverage beyond the openWorldHint. The pricing note is not behavioral. Since annotations already hint at open-world behavior, the description adds some context (time period, scope) but not much beyond that.

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 concise, with a clear definition, exclusions, and typical questions. It includes a pricing note which is somewhat extraneous but relevant. The structure front-loads the core purpose. However, the pricing note is not part of the description proper and may be considered noise, but it doesn't hurt. Overall, it's well-organized and doesn't waste words.

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?

Given the tool has an output schema (though not shown in the prompt but indicated), the description does not need to explain return values. It covers the query context, typical usage, and exclusions. The tool is relatively simple with only two params. The description is adequate for an agent to select and invoke correctly. Slight gap: it doesn't mention the 'year' parameter's optional nature explicitly, but the schema does. Overall, complete.

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 describes both parameters (park_name and optional year) with examples. The description reinforces the park_name usage by providing typical examples. It does not add meaning beyond the schema for parameters, but the schema coverage is 100%, so baseline is 3. The description adds typical question phrasing, which helps in understanding how to phrase the query. This pushes it to 4.

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 clearly states the tool queries the count of enterprises that have made external investments in the last two years based on a specific park name. It distinguishes itself from sibling list tools by explicitly noting it returns a count, not a list, and specifies exclusions. However, it doesn't explicitly differentiate from other '_num' tools in the same sibling group, which share a similar pattern.

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 provides typical question phrasings and states what is not included (other enterprise categories, list details). It implies usage when a count of investing companies is needed for a park. It does not explicitly mention when to use an alternative tool (e.g., the list variant), but the sibling naming convention ('_list' vs '_num') makes it clear. No explicit when-not-to-use guidance.

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