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

The annotations already declare readOnly=true, idempotent=true, destructive=false and openWorld=false, so safety is covered. The description's contribution is the scope disclaimer that results are neither savings estimates nor filing-ready conclusions, which is genuinely additive. It says nothing about cost, rate limits, or how sensitive the lookup is to the address versus PIDN form.

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?

Two sentences, no padding, and the negative scope statement is placed last where it functions as a boundary. The wording is dense with internal terminology but not repetitive or bloated.

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?

The tool is read-only with no output schema, so the description carries the burden of explaining what 'readiness' results look like, and it only gestures at this ('missing evidence'). Combined with the undocumented required address/PIDN parameter, an agent has enough to call it but not enough to interpret or confidently supply the identifier.

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 only 50%: county_key is well documented in the schema itself (adapter key, restricts scan, rejects conflicting prefixes), but address_or_pidn has no description anywhere. The tool description does not mention either parameter, so it does nothing to compensate for the undocumented required address/PIDN input or its accepted formats.

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 the object 'retained assessment/building observations' do name a specific resource, and the phrase 'method-specific missing evidence' hints that the output is a diagnostic gap report. However, terms like 'separate classification axes' are internal jargon that an agent cannot resolve into a concrete result without calling the tool, and no sibling is named for contrast.

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?

The 'for local Development testing' clause gives a context of use, and 'This does not establish savings or filing readiness' usefully excludes a neighboring use case (savings/filing determination, presumably audit_property_tax or simulate_property_model). There is still no positive statement of when to prefer this over those tools, and no prerequisites or ordering advice.

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