audit_log

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

With no annotations, the description carries the full behavioral burden, and it discloses exactly one trait: the trail is append-only, which usefully signals immutability. It says nothing about pagination or the meaning of limit, default ordering, whether wallet_id scopes the results, volume/size of the response, or any auth requirement — all material for an agent deciding how to call a log-listing endpoint.

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?

It is short and front-loads the defining concept, but it is written as two sentence fragments rather than a statement of what the tool does. The trailing 'The evidence of what was authorized' is evocative rather than informative and could be spent on the filtering and limit semantics instead.

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 simple two-parameter read tool this should be easy to complete, yet with no annotations, no output schema, and 0% parameter coverage the description leaves ordering, defaults, and result shape unstated. The enumeration of event types is genuinely helpful, but an agent still lacks enough to call it confidently with or without filters.

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 both parameters rest entirely on their bare names. The description never mentions that wallet_id filters the trail to one wallet or that limit caps the number of entries, so an agent must guess at the interaction between the two and at the default when limit is omitted. Two self-descriptive names keep this above the floor, but the description contributes nothing.

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?

The description names the resource and enumerates the event types it covers (policy grants, payments, rejections, approvals, revocations), which distinguishes it from the transactional siblings. However, it never states a verb — nothing says whether this lists, fetches, or streams entries, or whether it returns one record or many. An agent can infer a read of audit entries, but only by inference.

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?

There is no statement of when to reach for this tool versus check_payment, get_wallet, or the approve/deny siblings, and no prerequisites or exclusions. 'The evidence of what was authorized' gestures at a use case (verification/provenance) but is not an actionable trigger condition.

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