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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds real value beyond that: it names the specific databases consulted, the class of violations considered, and the legal basis for the computation, which tells the agent this is a deterministic internal-data audit rather than a live external query. It stops short of noting data freshness, coverage limits, or failure modes when a jurisdiction lacks blight records.

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?

One dense but well-ordered sentence that front-loads the action, the data sources, and the deliverable. The legal citations and parenthetical examples earn their place as scoping information; only minor tightening would improve it.

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 must carry return-value context, and it only names the deliverable artifact (Exhibit B-1, deduction figures) without describing the response structure, findings list, or how 'json' versus 'html' output differs. For a multi-source audit tool with a 6-parameter schema, that leaves a meaningful gap for an agent trying to interpret results.

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 100%, so the schema already explains all six parameters including parcel_id, address, jurisdiction, market_value, format, and county. The description adds no parameter-level meaning — notably it never explains how market_value feeds the deduction calculation or how jurisdiction/county interact — so the baseline 3 applies.

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 uses a specific verb ('Audit a parcel') against an enumerated set of data sources ('municipal code enforcement and 311 blight databases (unfit dwellings, demolition orders, exterior violations)') and states the output artifact plus legal authority. This clearly separates it from siblings such as audit_parcel_soil_capability, audit_parcel_topography, or audit_municipal_permits.

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 use case is implied by the stated goal ('calculate statutory obsolescence deductions and generate Exhibit B-1'), which tells an agent this is for valuation-reduction work. However, there is no explicit when-to-use/when-not guidance and no named alternative for overlapping tasks like permit or code-enforcement lookups done by sibling tools.

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