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

Beyond the annotations it discloses the side effect ("A succeeded build puts every held change live with its output"), the async ticket/polling model, that execution happens off the app server, and the authorization constraint ("Admins only"). It does not contradict the readOnlyHint=false / destructiveHint=false / idempotentHint=true profile; a successful build changes live state without deleting anything.

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?

Purpose is front-loaded and nearly every clause carries information (prerequisite, side effect, polling, auth). It is slightly elliptical telegraphic prose ("answers a ticket at once," "what assets/ holds is what the page loads") that costs a beat of parsing, but nothing is redundant.

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 correctly explains the return contract (an immediate build ticket, then poll get_build) and the success consequence, and covers permissions and prerequisites. The one real hole is the undocumented `theme` argument, which matters for a 2-required-parameter tool.

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?

Only half the parameters are schema-documented, and the description doesn't close the gap: `site` is merely re-referenced ("named in site") while the schema already explains it, and `theme` is a bare string with no description anywhere, so the agent gets no hint whether it takes a slug, handle, or display name from list_themes.

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?

"Asks for one build of the theme as it stands (its package.json scripts.build, off the app server)" names the exact verb, resource, scope and execution mechanism, and "poll get_build until it finishes" separates it from the sibling that reads build status.

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-not guidance: because "a write asks for its own build," this is reserved for "a build that failed on something outside the theme." It also handles the zero-build case ("A theme with no build needs none") so the agent knows not to call it for a plain asset directory.

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