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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds substantial context beyond them: a tiered credit cost (5 complete / 3 on source failure or missing reference file / 0 if the point cannot be resolved), partial data availability ('value and last sale only where stored'), and scope limits ('no owner data', 'not a flood determination, not a consumer report'). This is exactly the behavioral detail annotations cannot express.

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 purpose, then outputs, privacy constraint, input modes, cost, and disclaimers — a sensible ordering with almost no filler. It is dense and long-ish for a single block, but each clause adds a distinct fact an agent would otherwise have to guess.

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, the description still enumerates the returned data categories and flags partial availability, and it documents cost and failure modes. Remaining gaps are the response shape (field names/structure) and behavior for ambiguous or incomplete location inputs (e.g., zip alone, or conflicting lat/lon plus address).

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% for 8 parameters, so the description carries the burden and does explain the three valid locating combinations. However, zip, city, and units are never mentioned or constrained (e.g., units only appears obliquely via 'loan limits (1-4 units)'), and it does not say what happens if only zip or city is supplied.

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 and resource ('Mortgage property pre-check for one location') and then enumerates the exact outputs: county/tract, FFIEC income level and CRA flags, FHFA/HUD loan limits, USDA eligibility, FEMA flood zone and parcel facts. This is clearly distinguishable from siblings like query_parcels and site_screen without opening any schema.

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 explicit input modes (lat+lon, address+state, parcel_id+state) and hard exclusions ('Property data only: do NOT send borrower names, income, SSN or loan amounts'), plus a downstream-usage caveat ('verify before any Loan Estimate or credit decision'). It stops short of naming when to prefer a sibling such as query_parcels or site_screen, so the alternative routing is left implicit.

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