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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the bar is lower. The description adds value by disclosing return semantics: per-activity description, linked_kr_id, run count, all-time quality/approval as_of last run, and the nuanced meaning of unaligned, including that agent-level objectives do not count.

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?

Four dense sentences, each earning its place: scope, returned fields, semantic clarification of a tricky flag, and usage rationale. There is no fluff or repetition.

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?

There is no output schema, so the description compensates by enumerating returned fields and clarifying the non-obvious unaligned flag. It does not enumerate every possible flag value or pagination behavior, but it gives enough for an agent to invoke and interpret the audit 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 description coverage is 100%, and both parameters are already well documented in the schema, including that company_id is usually auto-injected. The description adds no additional parameter-specific insight, so the baseline 3 applies.

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 precise verb and resource: 'Audit all agent activities,' and names the three audit dimensions (staleness, business outcome alignment, cross-agent overlap). It also specifies the concrete per-activity fields returned, which makes the tool's purpose unmistakable and distinct from sibling getters like get_agent_performance.

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 provides a clear usage directive: 'Use this to apply first principles: question every activity before optimizing it.' This frames when an agent should choose the tool and its philosophy, although it does not explicitly name alternatives or when-not-to-use conditions.

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