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

Annotations already carry the safety profile (readOnly, non-destructive, openWorld), so the description's added value is the edition gating that produces an HTTP 403 and the underlying endpoint. Those are real behavioral facts an agent cannot get from structured fields. It stops short of describing pagination or volume characteristics, which keeps it from 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?

Three short sentences: resource definition, parameter prerequisite, then the edition/error caveat with the endpoint. No filler, and the scope constraint is front-loaded.

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 three-parameter read-only list with full schema descriptions and annotations present, the description supplies the two facts structured data omits (OR-scoping requirement, edition gating). It does not cover what happens if both IDs are passed or how results are ordered/limited, which is a minor remaining gap.

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%, so the baseline would be 3, but the description adds something the schema does not encode: the schema lists no required fields and no oneOf constraint, while the description states that one of lead_id or user_id must be supplied. That squarely compensates for the missing required-parameter signal.

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 defines the resource precisely — post-sales task checklists generated from a template, scoped to one lead or one user — which is more informative than the title alone. It lacks an explicit verb, but the 'GET /follow_ups' trailer and the 'of one lead OR of one user' scope make the operation unambiguous and clearly distinct from sibling list tools (activities, leads, comments).

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?

'Needs lead_id or user_id' gives the caller the concrete precondition for a successful call, and the HTTP 403 note warns ahead of time that the call will fail on non-higher-edition accounts. There is no explicit when-not guidance, but no sibling tool overlaps this resource, so there is little alternative to disambiguate against.

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