FacilityProof

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

With readOnlyHint=false but destructiveHint=false, the agent needs to know what side effect exists, and the description explains it: a $1.00 MPP charge, that identity/state eligibility are resolved before payment, that ambiguous/unresolved/unreleased requests are not charged, and that the call does not alter regulatory records. The idempotency nuance (fresh invocation can re-charge; settled-delivery retry must reuse the identical request and payment credential) goes well beyond the idempotentHint=false annotation and materially guides correct invocation.

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 core purpose and usage guidance are front-loaded, and the operational/billing sentences are dense rather than padded. It runs long, and the final sentence on settled-delivery retries is a lot of detail, but every sentence carries operative meaning for a paid, gated operation, so it stays efficient.

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?

An output schema exists, so return-value detail is not needed, and the description covers the remaining gaps an agent must know: identity-resolution strategy, released-state eligibility (CA/TX/FL), payment and non-charge conditions, and the read-but-charged side-effect profile. Nothing needed to call 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?

Schema description coverage is 100%, so the schema already documents each parameter, including the frsId-vs-name preference and the identity-hint role of zip/city. The description reinforces the resolution ordering (frsId/programId, else name plus location) and notes resolution happens pre-payment, but adds no new syntax or format meaning 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?

The description opens with a specific verb+resource ('Resolve one physical U.S. facility and return a bounded, source-reconciled environmental regulatory evidence report') and enumerates exactly what the report covers (air, water, hazardous-waste, drinking-water, inspections, violations, enforcement, penalties, freshness, gaps, conflicts). This scope is specific enough to distinguish it from the sibling permit-identity tool, which it also references.

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 states when to use it ('when an agent needs evidence about one specific facility and wrong-site matching or missing-source inference would be costly') and explicitly lists when not to ('company-wide research, raw EPA record retrieval, legal advice, or a clean/compliant verdict'). It also gives identity-resolution ordering (frsId/programId first, else name plus location), leaving nothing to inference.

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

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

Adds substantial behavioral context beyond the annotations: a $0.10 USD cost gate, current jurisdiction readiness (40 states), a fail-closed pre-payment rejection model, and a bounded scope disclaimer ('does not determine compliance, permit status, violations, enforcement, or penalties'). This tells the agent about cost, failure modes, and coverage limits that the readOnly/openWorld/idempotent hints cannot convey.

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?

Front-loaded with the core resolve-and-return action, then cost, readiness, failure modes, and scope limit. Every sentence carries distinct information, though the readiness/cost sentences are dense and could be trimmed slightly without loss.

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 values need no explanation, and the description still covers cost, jurisdictional readiness, fail-closed behavior, and explicit scope exclusions. An agent knows the inputs to supply, the expected charge, and the limits of the result before calling.

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 each of the seven parameters is already documented in-schema (FRS ID format, ZIP pattern, name/address hints). The description only restates the schema-level strategy of supplying an exact identifier or a name plus location context, adding no new syntax or format meaning. Baseline 3 applies when the schema carries the param burden.

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 ('Resolve one physical U.S. facility and return authoritative FRS environmental program/permit identifiers'), plus the scope of what is returned (jurisdiction and source-system provenance). The closing clause 'before deeper compliance research' implicitly distinguishes it from the sole sibling facilityproof.check_facility_compliance_evidence, so an agent can route between them from the definition alone.

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?

Clearly frames the position in the workflow ('before deeper compliance research') and enumerates the failure conditions that lead to rejection (ambiguous identity, medium-confidence identity, linked-record conflicts, missing routed program identity, Tribal/federal carve-out states). It never explicitly names the sibling tool or states when NOT to use this in favor of compliance evidence, so routing is inferred rather than stated.

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