a4a_get_counterparty_evidence

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

With no annotations present, the description carries the full burden and does so unusually well: it declares non-effects ('publishes nothing, reads no private mail, creates no profile'), discloses that 'the query is visible to the configured relay', and explains the trusted-issuer configuration. It also preempts over-interpretation by stating the output is not a fraud score, authorization, or proof of work, and that high scores do not remove unknown recovery history, devices, or controller information.

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?

Purpose is correctly front-loaded, but the caveat block is over-stuffed with overlapping disclaimers — 'NOT a fraud score, authorization, or proof of work', 'does not prove a unique identity or replace a current attestation-status check', and 'a high score does not remove these limitations' restate the same epistemic caution three times. Tightening these would improve signal density without losing meaning.

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 no-annotation, two-parameter tool, the description covers the essential burden: effects, privacy exposure, configuration prerequisites, coverage caveats, and data provenance ('event dates are signer claims'). An output schema exists, so return-value documentation is not required, though error/empty-result behavior and any latency or rate expectations are unspecified.

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 coverage is 0%, so the description must supply all parameter meaning, and the Args block does: pubkey is documented as a hex public key and days as a claimed-date window bounded 1–365 with default 30. It lacks guidance on invalid input handling (out-of-range days, malformed pubkey) or whether days bounds the reviewer-activity sample, but the core semantics are covered.

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 ('Read counterparty evidence') and enumerates the payload (ratings, author concentration, frequency by claimed dates, signed agreements, reviewer sample). It does not explicitly name which sibling it differs from — a4a_get_reputation and a4a_check_authority overlap heavily — so an agent must infer the distinction from content rather than an explicit pointer.

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?

'before choosing a customer or provider' gives a clear situational trigger for invocation. However, it never names the alternative tools for adjacent needs (reputation lookup, authority check, attestation status) or states when not to call it, leaving the sibling boundary to inference.

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