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

Goes well beyond the annotations: discloses tracking behavior (visit-level assignment, nothing stored for anonymous visitors), that it reads 28 days of page data, that it computes required sample size and duration from mde, that low-traffic pages still start with "not enough yet" status, and what is returned (variant-ship code for Next.js or plain HTML). Those are exactly the side effects and outputs an agent cannot get from readOnlyHint/destructiveHint=false.

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 purpose, then progressively detail. Nearly every sentence carries information, including the trailing "The control is the first variant" and "Free." The tracking-mode sentence is the densest and slows first-read comprehension slightly, keeping it off a 5.

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?

No output schema exists, and the description covers the return value (the code to ship as a PR) and the success-but-early state ("not enough yet"), which is the critical piece. It leaves unaddressed what happens on a duplicate or conflicting key and whether recurring tests per page are limited — minor for a non-destructive create.

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 75%, so the baseline is 3; the description earns an extra point by explaining the one parameter the schema leaves bare — mde, its default of 0.2 and its 20% meaning — plus reaffirming that the control is the first variant. Site, key, path, goal and hypothesis are already documented in the schema, so no further compensation is required.

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 — "Size and start an A/B test on one page against one goal" — which is far more precise than the title alone. The "one page" scope implicitly separates it from app_experiment_create, but no sibling is named explicitly, so an agent must infer the boundary.

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 through scope (one page, one goal, control first) rather than stated: there is no explicit "use this when..." or pointer to experiment_results / experiment_close for the follow-up or to app_experiment_create for app tests. The "quiet page is never refused" note does pre-empt a real agent concern (insufficient traffic), which is a partial when-not clause.

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