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

With only readOnlyHint=false, idempotentHint=false, destructiveHint=false in the annotations, the description carries the behavioral load well: it replaces the running server, refuses builds backed by sleeping database/cache, bills from the wallet (with a balance/pricing pointer), and preserves the server's size and always-on setting (with none running, the last values), noting always-on costs more. That is far more than the annotations convey.

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?

The behaviorally important facts (original settings preserved, build id source, cost, confirmation) are front-loaded and every clause carries information, but the single mega-sentence with nested parentheses, em-dashes and mixed capitalization is hard to parse and would benefit from being split into two or three sentences.

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 4-param mutation with no output schema, the description covers prerequisites, refusals, cost/auth (wallet), and override behavior, and points to docs for edge cases. It stops short of describing the immediate return (job id? server status?) or failure handling after the call, which an agent would want before invoking a paid, server-replacing operation.

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 baseline is 3, but the description adds real semantics: internalPort, subdir and gitRef override just that one setting, and subsequent rebuilds of the new build inherit the change. It also ties buildId to its source (lavela.compute_build_status) and explains the empty-string defaults implicitly.

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 — 'Start a finished repo build again with EXACTLY its original settings' — and lists the preserved settings (branch, folder, port, env, mounts). It clarifies the workflow ('how a server lavela built from a repo is REDEPLOYED after a push or a fix'), but never names or distinguishes itself from the sibling tool lavela.redeploy, which an agent could easily confuse it with.

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 a clear triggering context (after a push or a fix), a hard prerequisite chain (get the id from lavela.compute_build_status, only `rebuildable` builds), a refusal condition (sleeping database/cache refused), and an explicit instruction to confirm cost with the user before calling. Missing is an explicit when-not/alternative statement relative to lavela.redeploy or provision_compute_from_repo.

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