chemdraw_polish_document

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

With only bare annotation hints (readOnlyHint=false, destructiveHint=false), the description richly discloses behavior: it never edits the source, requires an extra feature, fails closed on unsupported content, preserves specific chemical attributes, does not auto-clean, and explicitly warns that checks establish preservation not correctness. This far exceeds the annotation baseline and gives agents essential safety expectations.

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 but every sentence carries critical operational information; the main purpose is front-loaded in the first sentence. It is somewhat long and could be structured into bullet points for scannability, but it avoids filler and earns its length.

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 tool with 10 parameters, no output schema, and minimal annotations, the description covers behavior, limitations, prerequisites, and preservation scope well. It omits explanation for several styling/output parameters (gap, label_gap, pixels) and does not describe return values, but the core calling context is sufficiently complete for an agent to use it 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%, so the description must compensate. It gives meaning to 'layout' and the maps ('Row layout requires explicit fragment-to-caption and arrow-to-condition ID maps from analyze; unassigned text is rejected'), but it does not explain 'gap', 'label_gap', 'width', 'pixels', or 'preset' beyond their schema titles. Partial compensation only.

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 opens with a specific verb and concrete deliverables ('Create a new normalized native drawing plus editable CDXML, SVG, PNG, before/after HTML, recipe and audit') and immediately disambiguates from siblings by stating 'Never edits the source' and 'Does not run native cleanup automatically.' This distinguishes it clearly from chemdraw_edit_document, chemdraw_clean, and chemdraw_export.

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 provides explicit prerequisites ('Requires chemistry extra', 'Flat one-page drawings only') and failure conditions ('queries/groups/abbreviations fail closed', 'unassigned text is rejected'), plus a dependency on 'analyze' for row-layout maps. It doesn't explicitly name alternative tools, but the conditions effectively tell an agent when this tool is appropriate and when to avoid it.

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