List call activity feed

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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is handled. The description adds genuinely non-obvious behavior: the feed aggregates activities across a contact and its readable related deals (a permission-sensitive rollup), the sort order is fixed at pinIndex DESC, callStartedAt DESC, id DESC, and pagination terminates when cursor is null. It does not describe item shape, but that is largely schema/response territory.

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?

Short paragraphs each carrying a distinct fact: scope, feed composition per entity, sort order, required parameter, pagination. Front-loaded with purpose. Minor waste in the opening line duplicating the title and the bare 'See also GET /v1/call-activity' reference, which adds little for an agent that cannot issue raw HTTP calls.

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 burden of explaining returns, and it does so adequately: item ordering is fixed and the response yields a cursor for continuation. Remaining gaps are the item field set and interaction with the limit parameter's default/maximum, both of which the schema covers for limit.

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%, including the 'exactly one of contactId or dealId' constraint, so the description mostly restates what the schema already says. It does add one piece of meaning not in the schema: that the cursor must be followed until it returns null, which clarifies the pagination contract beyond the parameter definition.

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 ('List call activity feed') and then defines the exact scope: for a contact it returns direct contact call activities plus those from readable related deals; for a deal the mirror case. This clearly differentiates it from the sibling list_call_activities, which is implied to be a flat activity list rather than an aggregated feed. The only weakness is the first sentence repeating the title verbatim.

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 operational guidance ('Provide contactId or dealId', 'Paginate with the returned cursor until it is null') and an external reference (GET /v1/call-activity), so the agent knows how to call it and how to exhaust results. However it never states when to choose this over the sibling list_call_activities, nor any permission/prerequisite context for 'readable related deals'.

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