Confirm & Generate Visuals

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

Annotations declare destructive/openWorld/non-idempotent, and the description substantiates all three: it explains that duplicate calls create duplicate generations and double-charge credits, that work runs in the background for 30-120 seconds, and that a generation ID is returned immediately. It adds a concrete polling protocol (wait 15s, then every 10-15s until status "completed") and names the output destination (Canvora workspace plus preview/downloadable URLs) — none of which is inferable from the structured fields.

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 trigger condition and the override model, then the critical anti-duplication warning. It is long but nearly every sentence carries operational weight; the only waste is mild repetition of the get_generation polling instruction, which appears three times in slightly different framings.

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 credit-charging, non-idempotent mutation tool with 13 params and no output schema, the description gives a complete operational picture: trigger condition, override scope, re-plan escape hatch, async lifecycle, polling cadence, and where artifacts land. The remaining gap is per-parameter meaning, which is real but secondary to calling the tool safely.

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 0% across 13 parameters, so the description carries the full burden. It does name several in prose (style, brand, language, resolution, slide counts, formats implied via the carousel rule) and explains the default behavior of omitted params, but roughly half — conversation_id, workspace_id, design_style_id, embed_logo, include_cta, embedding_photos, use_exact_content — are never mentioned, including the sole required parameter.

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 — confirm and start a visual generation — and pins the precondition to an exact sentinel string returned by the chat tool ("READY TO GENERATE"). It is clearly distinguished from the chat sibling, which is named as the tool for re-planning design/content.

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?

Explicit when-to-call (only after user reviewed and approved), explicit when-not (never re-call when slow), and an explicit alternative for a distinct case: format or content changes go back to chat, not to overrides here. It even states a hard constraint on the override path (carousel format requires carousel_counts).

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