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

Well beyond the annotations, it discloses side effects (free apps not yet owned are claimed first, same as claim_free_app), what is never done (paid apps are not purchased), refusal behavior with exact fixes, the 10-minute link lifetime, and the $SITE_APPS_KEY vs browser-sign-in secret distinction. This is consistent with readOnlyHint=false and idempotentHint=false, and confirms nothing is destroyed. It does not cover rate limits or concurrency, so not 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?

Every sentence carries substantive information with no filler, and the purpose is front-loaded. However, it is a single dense block of roughly 250 words mixing tool behavior, installer guidance, and owner-communication instructions, which makes it harder to scan than a structured definition would be.

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 fully compensates by describing return contents (short-lived link, sha256, per-app requirements, download.command, download.needs) and the installation procedure. For a 5-parameter tool with complex side effects, an agent has everything needed to call and interpret it.

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 defines all five parameters. The description nevertheless adds meaning the schema does not fully convey: the implicit claim-first behavior of `apps`, the fact that Site Health is injected unless removed via `without`, and that `detail: true` surfaces the bundle manifest also present in the zip. The `site`/`site_domain` short-form relationship is only lightly restated.

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?

Opens with a specific verb+resource ('Prepare the download for one site') and enumerates the artifact contents (core, apps, skills, INSTALL.md, manifest, license, signature). It also distinguishes its behavior from siblings like claim_free_app, create_checkout and renew_updates by naming those flows explicitly.

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 explicit when-to-use rules: pass `apps` for requested apps, omit it to get every owned app covering the domain, use `without: ["health"]` to exclude Site Health, and use detail:true for the full manifest. It also states the exclusions — paid apps are never bought here and are refused with a create_checkout pointer — which routes the agent to the right alternative.

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