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

Annotations already declare destructiveHint=true and readOnlyHint=false, yet the description still adds value by stating that the branch is retained and that the tool is blocked during an in-flight publish. It stops short of saying whether the archived preview/worktree/WIP can be restored.

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 terse sentences, action-first, with the precondition last. No filler, though the telegraphic phrasing ("preview/worktree/WIP") costs some readability.

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 destructive, fully-required-parameter mutation with no output schema, the description omits recoverability, permission requirements, what state the build must be in, and what the caller gets back. The precondition and branch-retention notes are not enough to call it complete.

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 description coverage is 0% and the description mentions none of the three required parameters (workspace, build_id, confirm). The const:true on confirm is self-explanatory in the schema, but workspace scoping and build_id expectations get no explanation anywhere.

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?

Specific verb ("Archive") plus the resources it targets ("preview/worktree/WIP") and what survives ("retain branch"). It is clearly a distinct operation from siblings like builds_get, builds_open or builds_save, though the artifact names are internal jargon an uninitiated agent may not parse.

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?

"Unavailable while publishing" flags a precondition but there is no guidance on when to archive versus alternatives such as builds_sync, publish_revert or publish_cancel. Usage is implied by the archive-and-keep-branch framing rather than stated.

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