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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false); the description goes far beyond by disclosing credit-consumption semantics (invalid/risky/catch-all/disposable/unknown results consume zero records, previously owned contacts do not re-charge) and the suppression + real-time verification pipeline. It also states the customer-notification obligation, which no annotation conveys.

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?

The action and selection criteria are front-loaded, and the billing/verification edge cases that follow each carry real decision value. It runs long for a one-parameter tool, with some sentences (e.g. the zero-record enumeration) that could be tightened, keeping it just short of ideal.

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?

With no output schema and only safety annotations, the description does the heavy lifting on billing, verification outcome handling, and the pre-invocation customer notice. It does not say what an unlocked record actually returns (email, phone, or both), which is the one remaining gap for an agent deciding what to do with the result.

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 lead_id parameter already documents itself as coming from search_people, so the schema carries the load. The description repeats the provenance but adds no format, range, or validity nuance beyond it, which is the expected baseline when the schema is complete.

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 (unlock), a precise resource (one B2B contact), and the identifier that selects it (lead_id from search_people). An agent can immediately distinguish this from the sibling search_* and verify_email tools, which enumerate or validate rather than unlock.

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?

Gives a clear triggering condition ('only when the customer requests access to a specific contact') and a prerequisite step (the contact must first be identified via search_people). It stops short of naming alternatives, e.g. that search_people is what surfaces lead_ids or that verify_email handles standalone validation, so the routing is implied rather than exhaustive.

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