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

Goes beyond the annotations by disclosing the $0.49 USD charge, the fact that no winner is ranked (output semantics), and that unsupported/held jurisdictions fail before payment, i.e. no charge on rejection. This is meaningful context for a tool whose annotations flag readOnlyHint=false and idempotentHint=false, though it doesn't explain why a comparison is non-idempotent or whether repeat calls re-bill.

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?

Three tight sentences with the cost front-loaded so the agent sees the billing implication first. Every sentence carries information, though the opening price fragment reads as a slightly clipped fragment rather than prose.

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 an output schema present, return-shape details are not needed; the description still covers cost, cardinality, jurisdiction limits, and result semantics (no winner selected). Minor gap: it says "San Francisco" while the schema describes broader California jurisdiction support, leaving the actual supported geography slightly ambiguous.

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 the schema already documents the 2-3 item bound, the distinctness requirement, and every nested field. The description adds little beyond restating "distinct candidate sites" and the same-evidence-dimensions constraint, 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?

States a specific verb and resource ("Compare two or three distinct candidate... sites"), bounds the scope (2-3 sites, San Francisco), and explicitly disclaims what it will not do ("without selecting a winner"). It is immediately distinguishable from build_property_intelligence_pack, which it names as the single-site alternative.

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?

Explicit routing: "Use this for side-by-side site evidence; use build_property_intelligence_pack for one site." It also states an operating precondition (unsupported or held jurisdictions fail before payment), so the agent knows the call can be rejected up front.

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