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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description's job is to add context — it does, by warning that skipping the bundle silently drops hand-authored ui/app.js and prior fixes, and by noting the download_url is signed. It stops short of describing freshness, caching, or how a bundle differs from a staged one.

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?

Two sentences, zero padding, with the return modes front-loaded and the high-stakes warning placed last so it lands. Capitalized emphasis is used sparingly and only on the terms that change behavior.

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 compensates by naming what comes back (file list, signed URL, or inline file content). For a read-only three-parameter fetch this is nearly complete; minor gaps are whether the signed URL expires and whether the file list is 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 100%: file, project_uuid, and version_uuid all carry descriptions including the default-to-latest behavior and the ~120KB truncation cap. The description only restates 'via file=' and 'CURRENT (or a given)', adding little beyond the schema.

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 ('Fetch the CURRENT (or a given) PUBLISHED bundle') and enumerates the two return modes: file list plus signed download_url, or one file inline via file=. The 'PUBLISHED' qualifier and the version parameter implicitly separate it from build_stage_bundle and build_get_project.

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 an explicit when-to-use rule ('For ANY change request on an existing app, START from this bundle') and names the alternative to avoid ('re-authoring from scratch') along with the concrete cost of that mistake. That is the when/when-not/alternative structure in two sentences.

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