export_runtime

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

The annotations only declare readOnlyHint=false and openWorldHint=false; the description's contribution is the write target ('export directory') and that output is optimized runtime JSON. It says nothing about overwrite behavior, what happens to an existing file of the same name, how expectedRevision conflicts are surfaced, or what errors look like for a file-writing mutation.

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?

A single front-loaded sentence with no padding or redundancy. The brevity is efficient rather than sloppy, though the thinness is a completeness problem addressed in other dimensions.

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 four-parameter disk-writing mutation with a concurrency field and no output schema, the description is far too thin: no file naming behavior, no overwrite/conflict semantics, no precondition on validation. An agent could invoke it but cannot predict what it will do to existing exports.

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?

All four parameters (name, requestId, sessionId, expectedRevision) have 0% schema description coverage, and the description adds no meaning for any of them. Notably, expectedRevision is almost certainly a concurrency/optimistic-locking token, yet the description gives no clue that callers must supply a revision or how it interacts with sessionId.

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 ('Save'), a specific resource ('runtime JSON'), and the destination ('export directory'), which is materially clearer than a bare name restatement. It does not distinguish itself from siblings like export_svg, export_sequence, get_runtime, or save_project, so an agent must infer which export path is intended.

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?

There is no guidance on when to choose this over export_svg, export_sequence, save_project, or get_runtime, and no prerequisites such as whether the scene must first pass validate_scene. The word 'validated' hints at a precondition but never states whether validation happens here or must happen before.

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