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

Annotations already declare read-only and non-destructive. The description adds valuable context by noting the log is 'append-only' and 'newest first', which explains the immutable, ordered nature beyond what annotations provide. No contradiction with annotations.

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?

Two sentences deliver purpose, scope, ordering, filtering, and read-only status with zero filler. The description is front-loaded with the core verb and resource.

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 read-only, paginated list tool with an output schema and annotations, the description covers the essential behavior: purpose, scope, ordering, and filter. It does not explain companyId semantics or pagination token details, but these are partially inferable from the schema and required context.

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?

The description explains entityId as a filter for one record's history and implies pageSize/pageToken via 'pages through'. However, companyId, a required parameter, is only described as a 'UUID value wrapper' in the schema, with no additional meaning in the description. Coverage is 50%, so partial compensation.

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 identifies the tool as paginating through the append-only accounting audit log, specifying the exact scope (journal entries and chart of accounts) and ordering (newest first). It distinguishes from siblings like cap_table_list_cap_table_audit_events by explicitly stating 'accounting audit log'.

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 gives clear usage context: use when you need to see who changed what and when in accounting, and use entity_id for a single record's history. It lacks explicit exclusions or alternative tool references, but the context is unambiguous.

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