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

Annotations already declare readOnly/idempotent/openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context beyond annotations: a 15-minute provenance_token validity window usable on any replica, the consequence of omitting it (values labeled unverified_model_data), and an explicit data-accuracy contract about derived metrics. That is substantive disclosure, though it is framed around chart_render rather than this tool's own runtime behavior (pagination, rate limits, result shape).

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 bulk of the text is policy boilerplate about chart_render, provenance tokens, and attribution footers rather than this tool's selection or invocation. The one sentence that actually describes the tool is buried at the front and never expanded, so the description is both oversized and mis-prioritized for its stated subject.

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 10-action, 2-parameter connector with no output schema, the enum carries the action semantics well, and the description covers how to treat returned values. What is missing is any statement of return shape or pagination behavior for the list actions (offset/limit), which the agent would need to drive multi-page retrieval 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?

Schema description coverage is 100%: the action enum documents every action, its inputs, and the params object spells out the per-action parameter shapes. The description adds no parameter detail beyond the schema, so the baseline 3 applies.

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 opening clause names the domain and resources ('ActiveCampaign email marketing and CRM: contacts, lists, campaigns, automations, deals, and tags'), which tells an agent what data lives here. However, it never states a verb (fetch/query/retrieve) and does nothing to distinguish this connector from siblings like mailchimp_connector, klaviyo_connector, or constantcontact_connector. The actual per-action purpose is only recoverable from the input schema enum, not the description.

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?

The description gives detailed guidance on chart_render, provenance tokens, and attribution footers, but none of that tells the agent when to invoke this connector versus a competing email/CRM connector. There is no context on prerequisites (e.g., connection must be enabled via enable_connector) or when a different sibling is the better choice.

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