Read your audit log

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds real behavioral context beyond them: the 30-day-per-call window cap, that attestations are only Merkle-rooted once confirmed, and the exact auth paths required (buyer API key with 'audit' scope, buyer session, or connector sign-in). It does not discuss pagination behavior beyond the schema's cursor.

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?

Three dense sentences, front-loaded with what is returned, then the filter, then the constraints and auth. No filler or repetition of schema field names.

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 no output schema, the description carries the return-shape burden and does so ('each with its licence terms and on-chain attestation...'), plus range limits, filter semantics, and auth requirements. An agent has everything needed to call it correctly.

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 100%, so baseline is 3, but the description adds genuine semantic value the schema lacks: the 'at most 30 days per call' rule constrains what from/to may span, and the event_type filter values are put in context as 'event-class' selectors.

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?

Specific verb+resource: returns the account's audit records, one per licensed access, and enumerates the per-record payload (licence terms, Merkle root, inclusion proof). This is clearly distinguishable from sibling tools like list_licence_orders or get_compliance_dossier, which deal with orders and dossiers rather than access events.

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 gives usable context (filter by event_type, max 30 days per call, auth conditions) but never states when to reach for this tool versus list_licence_orders, get_compliance_dossier, or article_53_attestation. Usage is implied by the resource, not routed explicitly.

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