Create a Word document

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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world; the description adds useful behavior beyond that — multiple files written per call, a page-1 preview returned, optional docx encryption, and template text prepended to supplied blocks. It does not disclose the re-run/overwrite consequences of the non-idempotent write, which is the remaining gap.

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 sentences, front-loaded with the core verb and the capability set, then output formats and return value. The long enumerations are dense but each element maps to real schema surface, so little is wasted — though it reads as a feature list rather than a task-oriented summary.

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 22-parameter creation tool with no output schema, the description covers the authoring model, output formats and the preview return value, which is the right altitude. It omits nothing dangerous, though it could have flagged that output_dir/output_path are effectively required and how blocks ordering interacts with templates.

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 82%, so the schema already documents nearly every parameter; the description mainly re-lists content block types and formats that the schema's oneOf branches and enum already convey. The template example list ('letter, resume, report') even omits 'sample' that the schema includes, adding no new semantics.

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?

Opens with a specific verb and resource ('Write a new document with WordCraft'), then enumerates exactly what can be authored (headings, lists, tables, images, TOC, footnotes) and which formats it saves. However it never names a sibling to distinguish itself from edit_document or convert_document, so the reader must infer 'create vs modify' from the verb alone.

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?

'Starts blank or from a built-in template' implies the fresh-document case, but there is no explicit 'use this instead of edit_document when the document does not exist yet' and no stated prerequisites (e.g. output_dir required for new documents, which only appears in the schema). Usage is inferable, not guided.

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