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

Goes well beyond the annotations: discloses the x402 payment model, the 402 challenge flow, the PAID_NOT_DELIVERED failure mode after settlement, and instructs not to auto-retry or re-pay. It also discloses that assembly does not verify input-card signatures and that an unsigned manifest reports its signing status/reason — rich behavioral context not captured by readOnlyHint/idempotentHint.

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-loads the most decision-relevant facts (PAID, one obligation, endpoint) and keeps the failure/payment caveats tight. It is still dense and caveat-heavy across many sentences, but each sentence carries operational weight, so waste is low.

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 paid, multi-step, non-idempotent tool this is close to complete: payment acquisition, preview path, empty-bundle behavior, failure handling, and caveats on what the output does and does not establish. An output schema exists, so omitted return-value detail is acceptable.

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 obligation, subject, preview and x_payment. The description reinforces meaning (obligation names, subject intent, preview = count only) but adds little syntax or format beyond what the schema provides. Baseline 3 applies when the schema does the heavy lifting.

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: it assembles an evidence bundle for ONE named obligation (article-50, article-53, dora, cra) plus optional subject, and enumerates the payload (card objects with signature fields, inclusion proofs, OSCAL assessment-results wrapper, manifest). An agent can distinguish it from evidence_bundle_preview (free) and the other evidence siblings without opening schemas.

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?

Gives clear routing: use preview=true or the free evidence_bundle_preview tool to check counts first, and omit x_payment to receive the actual 402 challenge. It also states scope exclusions (no new measurement, no full OSCAL conformance, not a legal determination). However it does not differentiate this tool from the other evidence-emitting siblings (rwa_evidence, server_evidence, art50_marking_evidence).

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