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

Goes well beyond annotations, disclosing concrete behavioral traits: ~45s build window, 'building' status fallback, exportId polling, the one-export-per-account limit with alreadyExporting/projectId reporting, retryAfterSeconds on busy, and ~1 day link expiry with 130 MB file sizes. This is rich, decision-relevant context that annotations don't capture.

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?

Dense but front-loaded — formats and return value come first, then timeout/polling and concurrency edge cases. The 'Free.' prefix is minor noise, and the long run-on sentences pack a lot in, but virtually every clause carries operational value.

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 tool with no output schema, it fully covers return shape (download URL, status 'building', exportId, alreadyExporting, retryAfterSeconds), timing, and error/edge behavior. An agent has everything needed to call it, poll it, and handle contention.

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 75% and the description adds real meaning: it defines what 'bundle' contains (ZIP of all three plus page PNGs), clarifies epub is fixed-layout/Kindle ready, and explains the exportId check-on-earlier-export semantics. It does not explain includeBackMatter, which the schema handles with a default.

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 ('Builds the assembled book...returns a download URL') and enumerates the exact output formats (pdf, epub, cbz, bundle) with their distinguishing traits. Clearly distinguishes itself from aetherwave_comic_assemble by its final instruction 'Assemble first.'

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 names the prerequisite ('Assemble first.'), the alternative/exhaust path via aetherwave_get_job with exact kind/taskId/projectId arguments, and the condition for re-calling with exportId. It also states the concurrency behavior — one export per account — which is the key usage constraint.

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