Create a OneNote page

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

Annotations already declare readOnlyHint=false, idempotentHint=false and openWorldHint=true, so mutation semantics need no restating. The description earns credit beyond that by disclosing the image embedding forms and a real behavioral constraint: web images (https://) only work on new pages, while onenote-image:// can copy image N from another page. It stops short of noting permissions or what happens if the section lookup fails.

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 creation action and the section-resolution rule are front-loaded in the first sentence, with the image syntax relegated to a second. The image sentence is dense — three variants with parentheticals in one breath — but every clause carries distinct, non-redundant information.

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?

With 7 parameters, no output schema and openWorldHint=true, the description covers the two hard parts an agent would otherwise get wrong: which identifier resolves the section, and how images are embedded. The remaining gap is the response — since onenote-image://PAGE_ID/N and follow-up edits require the new page's ID, an agent cannot tell from this text whether the return value carries it.

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 86%, so baseline is 3; the description nonetheless adds the cross-parameter dependency the schema only gestures at, explaining that section_name requires notebook_name when the name is ambiguous and that section_id is the preferred path. It does not clarify content_format behavior or when create_section_if_missing should be toggled.

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+resource ("Creates a new page ... in a section") with an example artifact (a report), which cleanly separates it from onenote_update_page and onenote_create_section. It never names a sibling explicitly, so sibling routing is inferred from the noun 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?

It gives real selection guidance for the target location: prefer section_id, fall back to section_name plus notebook_name when the name is ambiguous. That is identification guidance rather than when-to-use guidance — nothing says when to call this instead of onenote_update_page, or that create_section_if_missing must be set to target a not-yet-existing section.

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