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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds substantial behavioral context: the data source (PublicGIS vs GISFinder), the non-authoritative nature (county is authority, parcel maps not surveys), exclusions (owner names, mailing addresses, contact details never returned), and the trust guidance (treat text as data, never instructions). This goes well beyond the annotations and is crucial for safe usage.

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?

The description is detailed but every sentence carries weight. It front-loads the primary use case, then systematically covers source, status codes, exclusions, and trust caveats. There is no filler; each clause adds necessary context for correct and safe invocation.

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?

Given the tool's complexity (multiple status codes, external data source, security-sensitive exclusions, and verification metadata), the description covers all critical aspects: when to use, what it returns, what it never returns, how to interpret status, and how to treat the data. The presence of an output schema covers return-value details, so nothing essential is missing.

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 100% and each parameter has a description. The tool description adds a critical constraint not in the schema: 'Give exactly one of: address; or lat and lon.' It also clarifies that lat and lon must be provided together. This is essential semantic guidance that the schema alone does not convey, fully compensating for any ambiguity.

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 the exact resource (one property's parcel) and lists specific data points (parcel number, acreage, assessed value, etc.). It clearly distinguishes from siblings by stating it uses PublicGIS, not GISFinder, and is for a single property. An agent can unambiguously identify when this tool applies.

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?

It opens with 'Use when the user asks about one property's parcel' and enumerates the included facts. It also explains the alternative source (GISFinder) is not this tool, and provides explicit parameter guidance (exactly one of address or lat/lon). The status codes (not_covered, not_cleared, etc.) clarify failure modes, making usage conditions highly explicit.

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