draw_batch

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

No annotations are present, so the description carries the full burden. It discloses the return format ('Returns OK n=<total> h=<created handles>') and reveals that operations can have side effects (e.g., the 'layer' op sets current layer). However, it does not state whether the batch is atomic, how errors are handled, or any permissions needed, which are notable gaps for a mutation-heavy tool.

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 dense and information-packed, opening with a clear directive and then systematically listing operation signatures. Every sentence serves a purpose, but the wall-of-text format with many operation types could be slightly better organized with line breaks or a table. It earns a high score for efficiency, but not perfect due to readability.

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 tool's complexity (many op types) and the absence of annotations or schema descriptions, the description provides essential operational detail and return values. It does cover the core functionality well, but omits edge-case behaviors like error handling, batch limits, ordering semantics, or coordinate/unit conventions. These are likely domain-known but still represent minor completeness gaps.

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 only defines 'operations' as an array of objects with additionalProperties true, providing zero semantic detail (schema description coverage 0%). The description compensates thoroughly by enumerating every operation type with its parameters, including optional ones like '[snap]' and clarifying notes for 'symbol', thus giving the agent complete parameter-level knowledge.

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 clearly states the tool's function: 'Execute many drawing ops in ONE call' and explicitly distinguishes it from single drawing tools by advising 'ALWAYS prefer this over single tools for 3+ entities.' It also lists all supported operation types, leaving no ambiguity about what the tool does.

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 explicit when-to-use guidance: 'ALWAYS prefer this over single tools for 3+ entities.' This directly tells the agent when to choose this tool over the many sibling drawing tools, satisfying the criteria for strong usage guidelines.

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