tb_audit_log

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

Annotations already declare readOnlyHint and idempotentHint. The description reinforces this by using 'Query' and adds the behavioral nuance that this traces authority events historically. It doesn't mention pagination limits or data retention, but given the annotation coverage, the additional context (grant/revoke/approval decisions) is sufficient for an audit-log tool.

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?

One short sentence, front-loaded with the verb and resource. Every word earns its place; no filler or redundancy.

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 read-only audit query with zero required parameters and full schema coverage, the description is complete. It doesn't need to explain return format since there's no output schema and the purpose is self-evident. Light on retention or ordering details, but these are reasonable omissions for this complexity level.

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 baseline of 3 applies. The description adds no parameter-level detail beyond what the schema already documents for actor, event_type, board_id, and limit. No gap here, but also no enhancement.

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 clearly states a specific verb ('Query') and resource ('historical audit trail'), and specifies the event types covered ('authority grants, revocations, and approval decisions'). Though sibling tools also deal with authority events, this is the only audit-log tool, so it is distinguishable without needing to name alternatives.

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?

The description implies this is for reading historical audit data, and the siblings tb_grant/tb_revoke/tb_approve make it natural to infer this is the read-side counterpart. However, it never explicitly says when to use this instead of querying live state, nor does it mention the alternative read tool tb_query. Contextual guidance is implicit, not explicit.

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