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

Discloses the $0.03 charge, the fail-before-payment behavior for unsupported jurisdictions, and the current single-jurisdiction coverage – none of which the annotations convey. It also explains why readOnlyHint is false (the call is billed), which is exactly the kind of context annotations cannot provide.

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?

Roughly fifty words in four sentences, front-loaded with the price and the action, then routing to alternatives and finally the failure semantics. No filler or repetition.

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 an output schema exists, return values need no explanation, and the description covers cost, coverage, alternatives, and failure modes. The only gap is that 'resolved property' is not explained (whether resolve_jurisdiction must run first), a minor omission for a repeat-polling tool.

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% and each parameter (address, since, city, unit, state) is documented in the schema, so the description owes little here. It reinforces that 'since' is a lower bound and cannot be in the future, but adds no format or constraint detail beyond the schema. Baseline 3 is appropriate.

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 – 'Find timestamped changes after an ISO 8601 since value across released evidence dimensions for a resolved property' – and pins the current scope ('comprehensive in San Francisco'). It also names the siblings it is not (check_permits, build_property_intelligence_pack), so an agent can distinguish it without opening a 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?

Gives an explicit use case ('repeat polling') plus two named alternatives with the condition that selects each ('current permit detail', 'full current snapshot'). It also states a failure precondition – unsupported or held jurisdictions fail before payment – which sets caller expectations before invocation.

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