list_activities

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

Annotations already declare readOnlyHint=true and destructiveHint=false, yet the description still adds non-obvious context: the endpoint is undocumented and could change without notice, 'since' is a verified server-side filter, and entry content is user-authored and must be treated as data rather than instructions (prompt-injection warning). These are genuine behavioral facts not derivable from the structured fields.

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?

Front-loaded with the resource and row shape, then usage triggers, then the filter caveat, then the reliability and safety warnings — a sensible priority order. It is dense and longer than typical, but nearly every clause carries distinct information; the injected-content warning and undocumented-endpoint caveat in particular earn their place.

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 carries the return-shape burden and does so — typed rows, acting user, apiClient, and entity refs are all named. Combined with the pagination note, filter semantics, and stability caveat, an agent has enough to call this and interpret the result without further discovery.

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%, so 'since' is the only parameter the schema documents; the description reinforces it (ISO-8601, server-side) but adds nothing on syntax beyond that. 'page' and 'perPage' are covered only by the vague phrase 'supports pagination', with no mention of the default page size or the perPage ceiling of 100, leaving half of the low-coverage schema unassisted.

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 — a global cross-entity activity feed across the tenant — and enumerates what a row contains (type, acting user, apiClient, refs). It explicitly positions itself against the per-entity alternatives ('one call instead of per-record entry fan-outs'), so an agent can distinguish it from list_party_entries, list_project_entries, list_entries, and list_opportunity_entries without opening any schema.

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?

Gives concrete trigger phrases ('what happened this week across the book', 'what did <user> touch today', 'which emails came in') and states the exclusion clearly: no per-entity server-side filter, so filter client-side on the returned refs. That is an explicit when-to-use plus a when-not-to-expect-server-filtering, which is exactly what an agent needs to route correctly.

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