List email activity feed

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

Annotations already declare readOnly, idempotent, non-destructive, openWorld, so the safety profile needs no restating; the description instead adds genuinely new behavior: cross-entity aggregation (related deals/contact are folded into the feed) and a fixed deterministic sort of `pinIndex DESC`, `createdAt DESC`, `id DESC`. It omits permission requirements and rate limits, so it falls short of a 5.

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 text is front-loaded with the purpose and then broken into short, scannable lines for feed composition, sort order, and pagination; nothing is padded. The 'See also GET /v1/email-activity' reference adds little for an agent already holding this tool and is the only low-value line.

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 read-only, no-output-schema list tool this covers the essentials: what each ID selector yields, how to page, and that results are deterministically ordered. It does not characterize individual feed item fields or error behavior when neither ID is supplied, but those gaps are minor given the 100%-covered schema and existing annotations.

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 100% and the 'exactly one of contactId or dealId' rule is already stated in both parameter descriptions, so most of the description's parameter content is repetition. The one real addition is the cursor termination contract ('paginate with the returned `cursor` until it is null'), which the schema's opaque-cursor text does not convey.

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 gives a specific verb and resource ('Retrieves an email activity feed for the requested contact or deal') and clarifies that the feed aggregates related entities, which implicitly distinguishes it from a flat activity listing. It never names a sibling such as list_email_activities or get_email_activity, so the differentiation is inferred rather than stated.

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 states the selection condition clearly: provide `contactId` for a contact feed (direct plus readable related-deal activities) or `dealId` for a deal feed (direct plus related-contact activities), and it explains the pagination loop with `cursor` until null. It gives no explicit when-not guidance and never contrasts with list_email_activities, which would have made this a 5.

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