list_activities

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description adds substantial behavioral context: it specifies ordering (newest first), the content of rows (typed, acting user, apiClient, refs), pagination support, and a critical caveat that this is an undocumented Capsule endpoint 'could change without notice'. This far exceeds the 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?

Multi-line but dense and purposeful, front-loading the core definition and then layering filters, use cases, and the caveat. Every sentence contributes value; the caveat at the end is appropriate. Slightly long but not wasteful.

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?

With no output schema, the description fully specifies expected return content (typed rows, user, apiClient, refs), ordering, pagination, and filtering semantics. It also discloses the undocumented nature of the endpoint, which is essential for safe use. Nothing an agent needs to call it correctly is missing.

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 coverage is only 33% (only `since` is described). The description compensates by explaining `since` as an ISO-8601 server-side filter and mentions pagination generically. It does not detail perPage/page specifics but the schema already provides defaults and bounds, so the description adds semantic meaning beyond the schema.

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?

States a specific verb and resource: 'Global cross-entity ACTIVITY FEED: everything that happened across the tenant, newest first' — it clearly lists the content and distinguishes itself from per-entity list tools by emphasizing the cross-entity scope and the explicit note that there is no per-entity server-side filter.

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 explicit example queries ('what happened this week across the book', 'what did <user> touch today', 'which emails came in') and explains when this is the right choice ('one call instead of per-record entry fan-outs'). Does not name specific sibling tools as alternatives, but clearly implies that per-entity filtering is not supported, which routes to other list tools.

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