Count matching companies (free)

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

Annotations already declare readOnly/idempotent/openWorld, so the bar is lower, yet the description still adds real billing behavior: the call never spends credits, and a realtime count costs $0.04 at Tier 0 list price. It omits latency and result shape, but the output schema covers the latter.

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 with the core purpose front-loaded and no filler. The 'As with count_leads' cross-reference is slightly indirect and forces the agent to consult another tool's text to resolve the pricing claim, costing it a point.

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 23-parameter tool with full schema coverage, an output schema, and complete annotations, the description supplies the missing piece an agent most needs before calling: the cost model and its position in the search workflow. Filter-level caveats (realtime-only fields, vocabulary validation) are already carried by the schema.

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%, so the baseline is 3; the description earns an extra point by explaining the cost consequence of the mode parameter (realtime is the only path that bills, at $0.04). It does not add anything about the 20+ filter parameters, which the schema already documents well.

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 operation (count companies matching an ICP) plus a second concrete output (the credit cost of pulling them), and positions itself explicitly as 'the first step before search_companies'. That distinguishes it from both search_companies and count_leads without requiring an agent to open any 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?

'The first step before search_companies' plus the note that realtime runs only when mode:"realtime" is passed explicitly gives clear sequencing and mode guidance. It stops short of naming when NOT to use it (e.g. use search_companies when you actually need rows), so it doesn't reach a 5.

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