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

With no annotations, the description carries the full burden. It discloses two useful traits: the return shape ({ok, ir, results, languages}) and the constraint that only baked-in canonical examples work here while novel inputs require the SDK. It still omits error behavior, entitlement enforcement details, and any auth/rate-limit context, so it is only partially transparent for a demo-gated tool.

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?

Three short sentences. The core capability statement comes after a bracketed metadata prefix ('Fuse product · entitlement...'), which is slightly front-loaded with non-behavioral noise, but the body is dense and mostly waste-free.

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 annotations, no output schema, and 0% parameter documentation, the description should do more heavy lifting. It explains the return keys and the demo restriction, but leaves both required parameters and error/entitlement behavior unexplained, so an agent still cannot confidently construct a valid call.

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 0% and both parameter descriptions are empty, so the description must compensate. It does not mention source_text or atom_name at all – not the expected format of source_text nor the role of atom_name. The only clue is that 'novel inputs via SDK', implying source_text must match baked examples, which is thin.

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?

The description gives a specific verb and scope: 'Polyglot emit to all 7 supported targets in one call.' That distinguishes it from the similarly named sibling render_polyglot_roundtrip_pure by emphasizing it emits to all targets rather than a roundtrip. The '7 supported targets' and return keys make the purpose concrete, though the jargon 'polyglot emit' and the bracket metadata add noise.

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?

It hints at a usage boundary – canonical demo examples work via R2 while 'novel inputs via SDK' – which implies when this tool applies and when it doesn't. However, there is no explicit when-to-use guidance relative to the sibling render_polyglot_roundtrip_pure, so the routing is only implied.

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