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

Annotations already declare readOnly/idempotent/non-destructive and openWorld=false, so safety needs no restating. The description adds real value beyond them: it discloses the two operating modes, the one-budget-at-a-time constraint, and — with no output schema — spells out exactly what fields come back, including agency cost context around the budget.

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?

Front-loaded with the capability and backed by two illustrative questions; every clause carries information. It is dense and runs long in the opening enumeration, but nothing is filler.

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 itself and does so thoroughly by naming every returned metric and the reverse-lookup result. Both parameters, both modes, and the boundary with get_pricing are covered.

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 both parameters (including the 800–100,000 ladder and exclusiveMinimum) are already documented. The description explains the mode-switch semantics of each parameter but adds no format or behavior detail the schema lacks; 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?

States a specific verb and resource and then enumerates the exact outputs (domains, inboxes, campaign emails/day and /month, new people, cost per email and per planned reply, month-by-month ramp) plus the inverse mode (smallest budget for N new people). It is clearly distinguishable from get_pricing, which is named as the price-list sibling.

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 two concrete example questions that map directly onto the two call modes ("how many cold emails does $3,000 a month buy?" vs "what budget reaches 5,000 new people a month?"). It also scopes the tool ("one budget at a time") and routes the whole-price-list case to get_pricing explicitly.

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