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

Beyond the annotations (readOnlyHint=false, destructiveHint=true, openWorldHint=false), the description discloses the economically important behavior: returned records can consume credits, estimate_cost=true returns an estimate without records or credit use, and a connected DealMachine account with paid access is required. It also names a concrete failure mode (filter_source_mismatch), though it does not explain pagination behavior or result caps.

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?

Front-loaded with the core behavior and return shape, followed by filter caveats, then the cost-preview toggle, then prerequisites and credit warning. Every sentence carries information; density is high with no filler, though the account requirement could be tightened.

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?

No output schema exists, so the description usefully enumerates return fields, and it covers the auth/paid-access requirement and the credit-cost implication of a destructiveHint=true tool. The remaining gap is pagination and sorting, which matter for a 7-parameter search endpoint that can cap results.

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?

With schema description coverage at 0%, the description must compensate and does so only partially: it explains locations (required, with OR semantics implied by the schema), filters (people catalog), fields (requested fields), and estimate_cost. The page, per_page, and sort parameters are given no meaning in the description at all.

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 gives a specific verb and resource ('Returns people matching locations and filters') and enumerates the returned fields (names, phones, emails, primary address, requested fields). It partly differentiates from siblings by noting filters come from the people catalog and that property filters produce filter_source_mismatch, but it never explicitly names people_count, people_get, or property_search as the alternatives.

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?

Usage is implied well: locations are marked required, filters must come from the people catalog, and estimate_cost=true is explicitly described as the no-cost preview path. However, there is no explicit statement of when to choose this over dealmachine_people_count, dealmachine_people_get, or dealmachine_property_search, and no exclusions are stated.

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