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

Annotations only cover the safety profile (non-read-only, open-world, non-idempotent, non-destructive). The description adds substantive behavior the annotations cannot: default async extraction, the blocking generate=true path and its quota cost, and the partial-failure guarantee that the card ID is preserved for resumption.

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?

Four tight sentences with the core action and accepted inputs front-loaded, then mode behavior, then the error-recovery guarantee. Nothing is wasted, though the mode/quota sentence is dense enough that it could be split for scanning.

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?

With no output schema, five parameters at 20% schema coverage, and no annotations on async behavior, the description carries a lot of weight and covers most of it: inputs, source shapes, sync/async modes, quota implications, and failure semantics. The gaps are brandId semantics and any hint of what the call returns on success beyond the card ID.

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 only 20%, so the description must compensate and largely does: it defines idea as the editorial idea, title as optional and brand-language, enumerates the source variants, and specifies what generate=true does. Only brandId is left undefined in both description and 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?

Opens with a specific verb+resource ('Create a content card') and enumerates the three accepted source shapes (article URL, raw text, uploaded PDF), which lets an agent separate this from create_content and create_content_source_upload without opening the schema.

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?

Explains the two operating modes clearly: background extraction by default versus generate=true waiting for extraction and then generating a script against the generate_scripts quota. It does not explicitly name sibling alternatives such as create_content_source_upload, so the routing guidance is implicit rather than explicit.

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