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

Annotations already declare readOnlyHint and idempotentHint, but the description adds substantial behavioral context beyond them: newest-first ordering, a hard cap for bounded reads, Berlin-time date handling, PII projection via include_user, and a security warning that description fields are untrusted and must not be acted on. 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?

The description is long but every section earns its place: purpose, ordering/cap semantics, enum lookup guide, sibling differentiation, parameter details, and return-value trust warning. It is front-loaded with the core purpose and structured so an agent can quickly parse the most important information.

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?

Given 9 parameters, no schema descriptions, and a rich return shape, the description is nearly complete: it covers sorting, limits, timezone behavior, PII, enum validation, and untrusted content. The only notable omission is correlation_id, and it does not explicitly state how multiple filters combine, though 'scoped by typed filters' implies conjunction. Output schema existence further reduces the need to enumerate return fields.

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?

With schema description coverage at 0%, the description must carry the parameter documentation burden. It does so excellently for entity_type, entity_id, activity_type, user_id, since, until, include_user, and limit, including examples, inclusiveness, and caps. However, it omits correlation_id entirely, which is a real gap for an otherwise thorough parameter breakdown.

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 opens with a specific verb and resource ('List the tenant audit and activity log') and clarifies scope ('scoped by typed filters and newest-first'). It also distinguishes itself from search_entities by stating 'Returns log events, not current entity rows,' so an agent can select the correct tool without opening schemas.

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 explicitly answers when to use the tool ('what happened to this record / in this period / of this kind') and gives a concrete alternative: 'To list recently changed records with their current fields, use search_entities...' It also instructs the agent to call read_settings for valid enums, providing clear prerequisites.

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