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

Annotations supply openWorldHint, idempotentHint=false and destructiveHint=false, and the description substantially adds beyond them: it requires the caller's APIFY_TOKEN, may consume Apify usage (cost), waits up to 60 seconds (latency), caps output at 1,000 source-linked rows, and does not modify government records. Auth, cost, timing and output bounds are all disclosed, which is strong; only idempotency/retention semantics remain unaddressed.

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?

Two dense sentences, front-loaded with the usage condition followed by behavioral facts. Efficient overall, though phrases like 'minimized, receipt-bound packet' and 'rights-first' are opaque branding rather than informative terms.

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 9-parameter gateway with a nested subject object, no output schema, and a receipt/retention model, the description covers runtime behavior well but leaves the parameter contract and the receipt-chaining semantics unexplained. It is adequate to start a call but not to invoke it confidently with the optional parameters.

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 0% across 9 parameters, so the description must carry the load. It implicitly maps its domain list onto the task enum (e.g. 'EPA facility' → epa_facility_evidence, 'China-facing intake' → china_counterparty_intake), but it never explains subject, evidence, retentionDays, batchReference, transactionGate, previousReceiptHash, or screenRestrictedParties — several of which are non-obvious fields (a sha256 receipt hash, a caller-policy gate toggle).

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 (routing supported evidence tasks into one receipt-bound packet) and enumerates the domains it covers (U.S. property, India company/supplier, restricted-party, EPA facility, China-facing intake). It is distinguishable from the single-domain siblings, though the abstract 'minimized, receipt-bound packet' phrasing adds jargon without sharpening the boundary against tools like epa-echo-facility-compliance.

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?

'Use for routing a supported ... task' gives clear triggering context that matches the task enum values. However, it names no alternatives or exclusions, so an agent cannot tell from this text when to prefer the more specific sibling tools (e.g. leie-exclusion-screening, epa-echo-facility-compliance) over this gateway.

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