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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's job is to add context — and it does, by warning that the funnel has a defined stopping point and that a column of zeros is not evidence of a payout failure. That is a genuinely useful interpretation caveat not available from structured fields, though it omits how the code list behaves (pagination/ordering) when include_codes is set.

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 core enumeration is front-loaded and dense, and the read-only boundary closes it cleanly. The clause about 'a column of zeros is not mistaken for a payout failure' is slightly verbose but carries real interpretive value, so it earns its place; the em-dash stacking makes it a single long paragraph rather than clearly separated concerns.

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-value burden and does so by listing the metrics returned and the optional per-code breakdown. The remaining gap is the limit parameter's default and truncation behavior, which matters for an agent deciding whether counts are exhaustive.

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 50%: include_codes already carries its own description, and the prose restates it as 'list the individual codes with their own counts', adding little. The limit parameter is undocumented in both schema and description — no default, no statement of what is truncated when it is hit — so the description does not fully compensate for the coverage gap.

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 names a specific resource (the referral programme's funnel) and enumerates exactly what it returns: code count, visits, referred companies, attributed revenue, and pending/paid rewards, plus an optional per-code listing. That is enough for an agent to distinguish this from the other *_summary siblings (payroll, sales, leads, etc.) without opening the 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?

It gives clear context for use and an explicit exclusion: approving or paying a reward is a financial act not available here, which stops the agent from attempting it. It stops short of naming the sibling or path that does handle approvals/payouts, so the agent knows what this tool is not but not where to go instead.

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