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

Annotations declare readOnlyHint=true, and the description reinforces this ('Free, read-only') while adding substantial context the annotations cannot carry: build duration, the ~20s wait ceiling, the meaning of a non-empty `error` on an 'ok' build, and the specific refusal codes (TRIAL_*, INSUFFICIENT_*_BALANCE, *_CEILING) that mean the build never ran and there is nothing in the code to fix.

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?

Front-loaded with purpose, then usage, then error-code interpretation, then the rebuild pointer — a sensible order. It is dense with backticked codes and parentheticals, and the trailing docs URL plus the long code list push it toward the verbose side, but nearly every clause carries operational information.

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?

There is no output schema, so the description must carry the return semantics itself — and it does, enumerating the status values, the warning interpretation, and the refusal codes with their meanings and remediation. Combined with the cadence guidance, an agent has everything needed to poll correctly and interpret every outcome.

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 100%, so the baseline is 3; the description earns an extra point by spelling out the routing logic between buildId and the projectId+service pair ('No buildId? Pass projectId (+ service)'), which is the one parameter decision an agent actually has to make. It stops short of documenting the wait values beyond what the schema already says.

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 ('Check a repo build') and immediately enumerates the three possible outcomes (building/ok/failed), so the agent knows exactly what this returns. It also names the sibling that performs the write action (lavela.compute_rebuild), cleanly separating this read-only check from the rebuild path.

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?

Explicitly covers the no-buildId fallback ('Pass projectId (+ service)'), the calling cadence ('builds usually take 3-6 minutes; each call waits up to ~20s — keep calling; don't start another build meanwhile'), and the only sanctioned way to re-trigger a build ('Build again only with lavela.compute_rebuild'). Alternatives and prohibitions are both stated, not implied.

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