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

Annotations only declare readOnly/openWorld/non-destructive, but the description adds the operationally critical facts an agent cannot infer: 120-second client timeout, mandatory caching, 15 credits per request versus ~20 for separate calls, and that this is the slowest endpoint. It also discloses partial-data behavior (nulls, 0 last_sold_price in non-disclosure states, empty comps in rural areas) and that sub-sections cannot be disabled.

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?

Heavy but well-organized markdown: return contents are front-loaded, then exclusions, then usage, then cost/performance. The high cost and latency justify the length. Minor waste: the first FAQ entry ('Why is this so much more than the individual endpoints?') restates the Performance section almost verbatim, and the 15-vs-20-credit comparison appears twice.

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?

For an expensive aggregate endpoint, the description covers everything an agent needs to call it correctly: cost, latency budget, caching, partial-data semantics, and which sibling tools cover the excluded signals. An output schema exists, and the description still usefully summarizes the returned sections for selection purposes without redundantly documenting field-level returns.

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?

There is one parameter and schema description coverage is 0% — the schema provides only an example string with no description. The description never discusses the address input at all: no format requirements, no statement about whether a parsed address or an ID is accepted, no guidance on geocoding or ambiguity handling. The lone example in the schema carries most of the load, making this adequate but with a real gap.

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 (aggregates 11 internal sources into a single 292-field property report) and enumerates exactly which signals are and are not included. The 'Does NOT include' list explicitly names the sibling endpoints (solar analysis, mortgage/lien, skip tracing), so an agent can distinguish this from get_solar_analysis or get_mortgage_lien_analysis 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?

Has a dedicated 'When to use it' section with three concrete scenarios (dashboard render, one-shot underwriting export, ML training snapshots) plus an explicit exclusion rule: 'Call the individual endpoints if you only need specific signals.' The FAQ reinforces the all-or-nothing constraint and routes partial-need cases elsewhere, leaving nothing to inference.

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