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

Annotations only declare the generic non-readonly profile; the description supplies the operationally important behavior: draft creation is free, credits are charged only at render, brief mode requires a positive balance and is capped at 20/hour, narration is never rewritten, image_url downloads are cleaned of EXIF/GPS and served by AutoShort, and mismatch warnings are surfaced. That is well beyond what annotations cover.

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?

Front-loads the free/draft distinction and the workflow before the per-field detail, and nearly every sentence carries unique information. It is dense and long for one paragraph, but the density is substantive rather than 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?

With no output schema, the description still names the return payload (draftId, scenes, estimatedDurationSeconds, estimatedCredits, warnings[]) so the agent knows what to show the user. Combined with the workflow, credit behavior, and verbatim-narration rule, an agent has everything needed to invoke this correctly and hand off to the next tool.

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 already 86%, and the description adds real semantic context: narration is read verbatim and never rewritten, each scene with a visual gets exactly that image plus the art style, image_url substitutes the user's own photo and is marked imageSource "your image", and targetDuration is preserved even when narration cannot fit. Minor gap: aspectRatio and artStyle's enum behavior are left 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?

Opens with a specific verb+resource pair ('Create a video DRAFT') plus the key qualifier that nothing is rendered or charged, which cleanly separates it from autoshort_render_draft and autoshort_generate_video. The Director-mode workflow makes the tool's role in the pipeline unmistakable.

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?

Gives an explicit four-step sequence naming the sibling tools (autoshort_update_draft, autoshort_render_draft) and the condition that gates each: agree a script first, render only after user approval when credits are charged. It also distinguishes the two invocation modes (scenes[] for an agreed script vs. brief for an AutoShort-written draft) with their different cost/rate-limit profiles.

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