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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds genuinely non-obvious behavior beyond them — a 2-credit cost and the failure mode where photoless listings return a null overall with low confidence. It stops short of describing latency, coverage limits, or how the external photo pipeline is sourced beyond 'listing's photo set'.

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?

Headers make it scannable, but the ordering is odd — 'What it returns' leads while the actual purpose and usage come later. The model-disclosure FAQ answers a question no agent asked, and the return-value section restates an output schema that already exists, so several sentences do not earn their place.

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?

An output schema exists, so the long return-value prose is redundant rather than necessary, but the description still covers pricing, the null-result edge case, and the correct alternative tool — enough for an agent to call this correctly. The main gap is the complete absence of input guidance for the sole required parameter.

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%, so the description is the only place the single input could be explained — but it never mentions the property_address parameter at all. It does not state whether a full street/city/state/ZIP string is required, whether partial addresses are geocoded, or what happens on ambiguous matches; only the schema's bare example hints at format.

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 names a specific verb and resource: an AI condition assessment (overall category, confidence, per-room breakdown, flags) for a US residential property. It partly distinguishes itself from the sibling property_condition_custom_photos, but only inside the FAQ rather than up front, and it never contrasts with get_property_info or get_updated_property_info.

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 an explicit 'When to use it' section with three concrete scenarios (MLS screening, AVM adjustment, photo pre-screening) plus a stated exclusion: listings without photos return null and should use property-condition-custom-photos instead. Both the when and the when-not, with the named alternative, are present.

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