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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description still adds genuinely useful non-schema context: nothing is persisted, searches never spend credits, only contact reveals are metered, and a read-only key may call it. That is real added value, though it says nothing about how large criteria sets are handled or what shape the count comes back in.

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?

Three short sentences, front-loaded with the action, then cost/persistence constraints, then the use case. No sentence merely restates the title, and the credit-cost caveat is exactly the kind of detail an agent needs before calling.

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 six-parameter, no-output-schema counting tool this covers purpose, persistence, billing implications and auth requirements — the things an agent needs before deciding to call it. The remaining gap is filter-combination semantics, which neither the description nor the high-coverage schema addresses.

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% with per-field examples, so the schema already carries parameter meaning. The description adds a rolled-up list of the criteria families but no semantics beyond the schema — notably it never says whether criteria combine with AND or OR, or whether empty arrays are allowed given that zero parameters are required.

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 opens with a specific verb and resource — 'Counts how many prospects match ad-hoc targeting criteria' — and scopes it as ad-hoc/unsaved, which implicitly separates it from the saved-ICP sibling refresh_icp_audience_size. It stops short of naming that sibling or any search-style alternative, so an agent must infer the boundary rather than read it.

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?

'Use it to size an audience and validate targeting' gives a clear when-to-use condition, and the ad-hoc/no-save framing signals it is the exploratory counterpart to saved-audience flows. There is no explicit when-not-to-use clause or named alternative for the case where an agent wants saved or exported prospects.

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