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

Annotations already establish readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description usefully adds that returned facts are nullable with source identity and explicitly enumerates what the tool will not infer (debt, equity, sale intent, life events, flood status, distress), which is substantive guardrail context beyond the annotations. It stops short of describing return shape or pagination.

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 short sentences with no filler, and the scope-limiting negatives are packed into one clause. It is front-loaded, though the opening sentence leans on undefined jargon ('retained', 'stacked leads') that costs more than it saves.

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 7 undocumented parameters, two enums, no output schema, and a domain-specific data product, the description leaves the agent without enough to invoke it correctly (what q matches, what 'signal: assessment' means, default limit/format, how pagination works). It explains boundaries but not operation.

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 description coverage is 0% across 7 parameters, so the description must carry the load — and it doesn't. It never mentions q, limit, offset, format (json/csv), or the single-value 'signal' enum, and only obliquely gestures at county/state via 'county availability is explicit'. An agent cannot infer filtering or pagination semantics from this text.

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 verb ('Inspect') and resource ('retained county property observations') are stated, but 'stacked leads' — the actual name of the tool's product — is never defined, so an agent cannot picture what a 'lead' record contains. The negative list (does not infer mortgage debt, equity, sale intent...) clarifies scope but doesn't describe what is returned, leaving the purpose partially vague relative to siblings like gisdb_get_cash_buyers.

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?

There is no statement of when to call this versus adjacent tools such as gisdb_query_notices, gisdb_get_cash_buyers, or gisdb_export_distress_feed. 'County availability is explicit' hints that some counties are unsupported but doesn't tell the agent how to check or what to do when a county is missing.

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