분자 구조식 그리기

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false), the description discloses the produced artifact formats, that formula and molecular weight are returned for self-checking, and the shape of error messages (atom #index, ^ marker) plus the expected retry behavior. That is real behavioral context an agent could not infer. It doesn't say whether files are written to disk or where, which is the main remaining gap for a non-read-only 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?

Four short lines, front-loaded with the verb and input format, then an example, a verification rule, and a failure protocol. The inline JSON example earns its space. Minor redundancy: the reaction notation is repeated from the schema's smiles description.

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?

There is no output schema, so the description's mention of SVG/PDF/PNG output, preview, formula, and molecular weight is necessary and present, as is error-handling guidance. What's missing is where output files land and what `kind` toggles behaviorally; those leave a small residual gap for a 5-parameter 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 60%, and the description adds meaning for the key parameter by spelling out the reaction syntax (reactants>>products) and showing a legend usage in the example. However, `kind`, `name`, and `show_atom_numbers` carry no explanation in either place, so the description only partially compensates for the coverage gap.

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 names a concrete verb and resource ("Draw a molecule or reaction from SMILES") and enumerates outputs (SVG/PDF/PNG, preview, formula, molecular weight). It also excludes a common wrong input with "(not a name)". It does not explicitly differentiate itself from the sibling render_tikz, so it stops short of a 5.

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?

It sets a clear input condition (SMILES only, not a name), supplies a worked example, and prescribes a verification step ("Check that formula and mol_weight match the intended molecule"). The retry instruction on failure gives an explicit recovery loop. No guidance is given on when to prefer this over render_tikz or export_document.

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