create_draft_figure_v1_figures_drafts_post

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

Without annotations, the description fully discloses behavioral traits: caps on inline_data (1000 rows/512KB, truncation with truncated flag), per-user soft cap (100 drafts per origin, 429 error), idempotency within 60 seconds using SHA256, and creates a private standalone figure.

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?

The description is well-structured with a header and bullet points for behavior, front-loading the purpose. It is not overly verbose, but could be slightly more concise by removing the HTTP method and auth line since that is structural.

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?

Given the complexity (5 nested parameters, no output schema), the description covers key behaviors like creation, limits, and idempotency. It lacks details on the response format (e.g., draft id) and does not explain all parameters in depth, but overall it is sufficiently complete for an agent.

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?

The input schema has no descriptions for individual properties, but the tool description adds context for inline_data (capping and truncation) and origin (per-origin cap). However, other parameters like viz_spec and transform_config lack explanation, though they are somewhat self-explanatory.

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?

The description explicitly states the tool creates a snapshot draft figure on the authenticated user's profile, with a specific verb ('Create') and resource ('draft figure'), and distinguishes from siblings by specifying it's for external clients with rendered data.

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 description provides a clear context for when to use this tool (external clients with rendered data wanting to hand off to the figure editor) but does not explicitly state when not to use it or mention alternatives. However, no direct sibling create tool exists, so this is adequate.

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