Text Generate

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

Annotations already disclose openWorld, non-idempotent, non-read-only behavior, so the bar is lower; the description still adds real context beyond them: no default account is borrowed, sources are treated as untrusted text, and hard token/currency ceilings fail when meters are missing. It omits the two-step dry_run/authorize_submission gating, which is the most consequential behavior for an agent.

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 short sentences, front-loaded with the core action, each carrying distinct information (capability, credential policy, input trust, failure mode). Slightly telegraphic, but no padding.

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?

An output schema exists, so return values need no explanation. However, for a tool whose defaults are dry_run=true and authorize_submission=false, the description omits the submission workflow entirely, which an agent needs to invoke it correctly.

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 100% and the nested request object is fully documented, so the baseline is 3. The description adds only constraint-level meaning (no file/media/grounding inputs) and does not explain fields like backend, dry_run, or authorize_submission beyond 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 and resource (generate structured text via one selected compatible HTTP endpoint) and adds exclusionary scope (no files, media, tools or grounded search), which separates it from vision/media siblings. It never names an alternative sibling or delineates from text-adjacent tools like content_analyze or vision_chat, so it stops short of full sibling differentiation.

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 'cannot accept files, media, tools or grounded search' line gives implicit when-not guidance, and 'one selected compatible HTTP endpoint' implies a prerequisite. There is no explicit statement of when to choose this over siblings, nor of what must be configured first (backend/account) before calling it.

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