summarize_activity

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

No annotations are provided, so the description carries the full burden. It discloses that counts are pre-computed in Python, that date boundaries are inclusive, and it exposes the exact return structure with summary and pagination blocks. It does not mention permissions, error behavior, or timezone assumptions, but for a read-only aggregation these are not critical.

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 well-organized with a concise purpose line, a usage warning, and clear Args/Returns sections. There is slight redundancy where the prose mention of 'Returns event counts...' is later repeated as a structured returns block, but the text is otherwise efficient and front-loaded.

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 two-parameter aggregation tool with an output schema present, the description covers purpose, parameter semantics, and return keys sufficiently. It lacks an explicit when-to-use-versus-siblings statement and has no annotation safety profile, but the core invocation details are complete enough for an agent to call it 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?

The input schema provides only bare string properties with 0% coverage. The description compensates fully by defining date_from as 'Start of the window, ISO-8601. Inclusive' and date_to as 'End of the window, ISO-8601. Inclusive', adding format, semantic role, and boundary inclusivity to both parameters.

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 states a specific verb and resource: 'Summarise all audit-log activity in a window', and enumerates the output dimensions (by actor, action, CRUD, access type, failure and anonymous rates). This clearly frames the tool as an aggregation over raw events and distinguishes it from siblings like list_activity_events or get_actor_profile.

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?

Provides a strong usage directive: 'Use these numbers directly; do not re-derive them from raw events.' This tells the agent to rely on pre-computed counts rather than computing from raw event lists, which is clear contextual guidance. It does not explicitly name alternative tools or exclusion conditions, but the implied comparison to raw event access is present.

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