drawing_import

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

Adds behavior the annotations cannot express: fail-fast semantics ('stops at the first failure'), the return of created IDs, and an explicit warning that partial writes are not rolled back. This tells the agent exactly how to reason about a non-atomic, non-idempotent mutation.

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?

Two dense sentences with zero filler: the first states creation plus verification, the second states failure and return behavior. The key safety caveat is front-loaded.

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?

Covers the return value (created IDs) despite no output schema and discloses the non-atomic failure model, which is the main risk for a bulk mutation. What's missing is guidance on the drawings payload structure, which the nested schema leaves largely undescribed.

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 67%, and the two scalar parameters already have descriptions in the schema (target_id, expected_layout_id). The description's 'per-item identity verification' hints at validation semantics but does not explain the drawings array, its shape/points structure, or what identity is verified against.

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 (create a bounded list of drawings) and adds batch semantics that separate it from the single-item drawing_create sibling. It never names drawing_create as the alternative for single items, so the differentiation is implied rather than stated.

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 implies bulk use and per-item verification, but gives no explicit guidance on when to pick this over drawing_create or when an import should be split into smaller batches. No prerequisites (e.g., layout must be open) are stated beyond what the schema fields already carry.

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