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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely new behavioral facts: no sign-in or purchase is required, the call returns source coverage, previews and available offers, and unsupported notice categories never silently fall back to assessment records — an important data-integrity guarantee. The one-question-at-a-time turn discipline is also a behavior 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?

Five short sentences, front-loaded with what the tool finds before the interaction rules and output shape. Every sentence carries information. Docking one point because 'Unsupported notices never fall back to assessment records' is telegraphic and reads as a fragment without the surrounding schema context.

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 an output schema present, the description needn't explain return values, and it correctly summarizes them as coverage, previews and offers while covering auth ('no sign-in'), cost profile, and the iterative turn model. For a tool with a 10-field nested answers object and 14 siblings, the remaining gap is routing guidance versus gisdb_continue_search and gisdb_start_search.

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 baseline is 3; the description earns above that by explaining the accumulation contract ('resend previous answers and skipped IDs'), which tells the agent the answers object is stateful across turns rather than a fresh filter each call. It adds nothing about preview_limit/preview_offset beyond the schema, but the protocol-level semantics it contributes are the non-obvious part.

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 opening sentence names a specific verb (find) and enumerates concrete resources: property records, owner-name groups, lead packages, county downloads. The phrase 'Ask one next_question at a time' signals this is a conversational/guided search, which distinguishes it in spirit from direct-search siblings like gisdb_search_records. However, it never names those siblings explicitly, so the boundary with gisdb_start_search and gisdb_continue_search must be inferred.

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?

'Ask one next_question at a time' plus 'accept unknown or skipped answers and resend previous answers and skipped IDs' gives a clear interaction protocol for continuing a session. What is missing is when to pick this over gisdb_start_search, gisdb_continue_search, or gisdb_search_catalog — the presence of a continue_search sibling makes the routing ambiguity material. Usage is implied by the protocol, not stated against alternatives.

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