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

Goes well beyond the annotations: it discloses the approval gate ('nothing changes in Apple Ads before' the founder approves), the vendor-number prerequisite for afterInstall data, the Apple platform limitation that starts cannot be tied to keywords, and the guardrail that blocks bid/budget increases when no starts occurred. Missing only volume/pagination or rate context for a data-heavy read.

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 action is front-loaded, but the description is one long chain of colon- and semicolon-separated clauses that takes effort to parse, and some of the proposal-type enumeration restates what could be one sentence. It earns most of its length but not its density.

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 no-output-schema, zero-required-parameter analysis tool, the description covers the data read, the target semantics, the afterInstall path, and the approval workflow. It does not spell out the shape of the returned proposals or how errors (e.g., missing vendor number) surface, which is the 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 schema already documents days, targetCpi, and targetCostPerStart, including the precedence rule. The description reinforces the target/per-start concept but adds no syntax, formatting, or defaults beyond what the schema provides.

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 (read) plus resource (Apple Ads: campaigns, keywords, search terms) and a second verb (propose changes) with concrete proposal types. It is clearly distinguishable from a pure apply tool, though it never names the sibling ads_propose that would complete the routing.

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?

Usage is implied rather than stated: the days window, the target parameters, and the condition that proposals wait for approval give context, and the afterInstall gate ('when not one started after enough installs no bid goes up') hints at when it applies. It never explicitly contrasts with ads_propose, ads_setup, or platform alternatives, so the agent must infer the choice.

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