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

Discloses substantial behavior beyond the annotations: one B2B credit per contact returned, a hard 100-contact cap, AND-across/OR-within filter semantics, the fact that addresses are warehouse-grade and not SMTP-checked, and cross-call dedup so repeated calls return new people. There is a mild tension with idempotentHint=true (repeated calls yield different results and consume credits), but the description is transparent about the actual behavior, so the mismatch lies in the annotation, not the description.

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?

Six dense sentences, each earning its place: core purpose, credit cost and the 100-cap, filter combination logic, keyword matching semantics, email-quality caveat, and dedup behavior. The cost constraint is front-loaded right after the purpose, and there is no filler.

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?

Remarkably complete for a 10-parameter, no-output-schema search tool: cost model, filtering rules, data-quality warning, and dedup are all covered. The remaining gaps are minor — return fields are not described and the free preview path (preview_b2b_leads) is never mentioned as a no-cost alternative.

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 adds genuine value beyond the schema: company_keywords matching semantics (company name, its own keywords, and industry tags) and the rationale for verified_email_only (addresses are not SMTP-checked), lifting it clearly above baseline.

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 states a specific verb+resource ('search the contact database') and enumerates the filter dimensions (job title, seniority, department, industry keywords, location), making the core purpose unmistakable. It does not explicitly name a sibling to distinguish from, and preview_b2b_leads is a near-twin that only the credit-spending note implicitly separates.

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?

Provides strong usage context: 'filter tightly' because a credit is spent per contact, set verified_email_only before sending cold mail, and company_keywords is identified as the right way to target a vertical. It never states explicit when-not-to-use conditions or names alternatives such as preview_b2b_leads for a free preview or verify_email for SMTP-checking.

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