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

Goes well beyond the annotations: it discloses that a preferred-site decision is emitted only when one site dominates, that there is no hidden weighted score, that missing evidence is never treated as clear, that address-only inputs degrade to point-radius screens, and that a temporary branded decision card is produced (congruent with readOnlyHint=false). These are exactly the behavioral traits an agent cannot infer from the structured fields.

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?

Labeled sections (Purpose / When to use / Returns / Limitations / Parameter guidance / Chaining) make it scannable and front-loaded, and every section carries information. It is on the long side, with the Returns list and the chaining note slightly overlapping on site_ref propagation.

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?

For an 8-parameter tool with nested site_ref objects and an output schema, the description covers the shared-input semantics, the evidence-asymmetry behavior, the decision-card artifact, and the chaining contract. Nothing an agent needs to invoke it correctly 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?

Adds real meaning beyond the 75%-covered schema: site_a/site_b accept either an address or a prior site_ref, intended_use and project_stage are shared across both sites, and proposal/no_go_triggers are 'applied equally' — a comparison semantic the schema cannot express. It does not mention radius_meters or the top-level site_ref fallback parameter, leaving small gaps.

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 precise verb, cardinality, and domain: 'compare exactly two UK sites for the same intended use and stage using the existing Site Verdict evidence.' This distinguishes it from the single-site siblings (site_verdict, analyze_site) without the agent needing to open any 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?

The 'When to use' clause gives a concrete trigger (after appraising one or two candidate sites) and an audience (architect/developer shortlist decision), and the Limitations section adds exclusions (does not replace acquisition, planning, or technical due diligence). It never names a sibling tool as the alternative for a single-site case, so routing is implied rather than explicit.

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