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

Annotations only cover openWorldHint and destructiveHint, so the description adds real value: it discloses that the result is cached on the profile and, crucially, that sizing is free / never spends credits while contact reveals are metered. It stops short of explaining cache staleness or the response shape.

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 tight sentences, front-loaded with the action and immediately followed by the cost model, which is the most decision-relevant fact. No wasted text.

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 single-parameter refresh tool with no output schema, the description covers the action, the caching side effect, and the billing behavior. The main missing element is whether the call can be slow or rate-limited given it hits a live provider.

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% and the single id parameter is fully documented with its source (list_icps), so the schema does the heavy lifting. The description adds no extra meaning about the ID beyond what the schema already states.

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?

States a specific verb and resource: re-counts prospects matching an ICP's targeting criteria against the live provider and caches the result. It is clearly distinguishable from listing/getting tools, though it never explicitly names the sibling get_audience_size it complements.

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?

Implicitly the tool is for refreshing a stale cached count, but it gives no explicit when-to-use vs get_audience_size or other sizing paths, and no prerequisites beyond requiring an ICP ID. Usage must be inferred.

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