site-due-diligence-bundle

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and idempotentHint=false, and the description explains the nuance behind that profile: it never writes to any external system but each call starts a metered run on the caller's Apify account. It adds cost rates ($0.10 per result, down to $30/1,000 on paid plans), the failure-billing rule ('nothing is charged when a run fails'), and the live-source read behavior — none of which the annotations convey. No contradiction with readOnlyHint=false.

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?

Long but information-dense and front-loaded, with clear 'CHOOSE THIS' and 'COST AND SIDE EFFECTS' sections. The store-page URL and the describe-gov-data-tool pointer are arguably marginal, keeping it from a 5, but no sentence is pure filler.

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 a metered, multi-layer screening tool with no output schema, the description covers purpose, routing, exclusions, cost/billing model, side effects, and source fidelity, and points to a free example-input tool. Nothing an agent needs to select or safely invoke it 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 assets, maxAssets, and radiusMiles in detail, including which layers honor the radius and which ignore it. The description adds per-site billing semantics ('one row per site, not per layer'), but that is the schema/annotations' territory rather than new parameter syntax. 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+resource and scope: a combined go/caution/no-go fatal-flaw verdict with a 0-100 score across 20 named federal layers, one row per site. It explicitly names the sibling it is not (an ASTM records review) and routes contamination-first questions to epa-contaminated-site-screener, so an agent can distinguish it without opening 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?

Explicit selection guidance: 'CHOOSE THIS when you want one combined go/caution/no-go verdict for a coordinate across many unrelated layers,' plus a negative boundary ('NOT an ASTM records review... omits coordinate-less Superfund records') and a named alternative for the contamination-first case. Alternatives and the condition that selects them are fully stated.

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