Count matching leads (free)

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

Annotations only declare readOnly/idempotent/openWorld; the description adds the decisive behavioral facts an agent cannot get elsewhere — this call never spends credits, the realtime count is a $0.02 flat charge, and the tool actively refuses to run one unless explicitly requested. That is exactly the kind of cost and gating context annotations do not carry.

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 sentences, front-loaded with the core question and the free/cost distinction, with zero filler. There is mild redundancy between 'FREE — this call never spends credits' and 'without paying per row', but the emphasis is justified for a cost-sensitive tool.

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 36-parameter tool with full schema coverage and an output schema, the description supplies the missing decision layer: cost, free-ness, ordering relative to search_leads, and the realtime escalation cost. Filter semantics are correctly left to the schema, though the interaction with the sibling preview_leads is not addressed.

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% and the mode parameter is already fully documented in the schema, including the auto/database/realtime tradeoffs. The description only reiterates the realtime gate ('unless you pass mode:"realtime" on purpose'), adding no syntax or format detail beyond structured fields, so baseline 3 applies.

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 first sentence names the exact question answered — how many leads match an ICP and what pulling them costs — which is a specific verb+resource and immediately distinguishes it from search_leads. An agent can tell what it produces without opening the schema.

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?

Explicit sequencing directive: 'ALWAYS CALL THIS BEFORE search_leads', with the rationale (only way to size an audience without paying per row). It also states the exclusion condition — realtime is refused unless mode:"realtime" is passed on purpose — so both when-to-use and when-not-to-use are covered.

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