ingest

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

No annotations are provided, so the description carries the full burden. It does disclose a real behavioral trait, that a browser download is 'moved out of Downloads', useful context absent from the schema, but it omits permissions, failure modes, and what happens to the stored asset on later collisions (beyond the schema's overwrite note).

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?

Two tight sentences that front-load the core action before enumerating sources. No filler, though the source list partially restates what the nested source schema already encodes.

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 9-parameter tool with a nested source object, no annotations, no output schema, and 33% coverage, the description covers the primary flow but omits behavior for preview, tags, parent, chat_url, and what the tool returns. Adequate but with clear gaps.

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 only 33%, so the description must compensate. It clarifies the source parameter modes ('download', 'URL', 'local path') and the 'record its prompt' purpose, but leaves tags, parent, preview, project, and overwrite entirely to the schema.

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) and resource (generated image or video into the project's raw/ or video/ folder) plus the secondary action of recording the prompt. It is more specific than the vague tool name 'ingest', though it does not explicitly distinguish itself from siblings like add_reference.

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?

The 'Source:' sentence enumerates the three accepted input modes (browser download, URL, local path), which implies when the tool applies, but there is no explicit when-to-use/when-not guidance or routing versus alternatives such as add_reference.

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