search-onenote-pages

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

Beyond the readOnly/idempotent annotations, the description discloses real behavioral traits: default ordering by lastModifiedDateTime, time filter semantics, unsupported full-text search with a specific error code, and a known failure mode for large accounts with an alternative path. These are exactly the kind of runtime behaviors an agent needs to predict success and avoid wasted calls.

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?

Three sentences, each earning its place: core behavior and example, a critical unsupported-feature warning, and a targeted fallback instruction. It is front-loaded with the primary action and scoping, and the caveats are compact.

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?

The description, combined with the rich input schema and read-only annotations, gives the agent everything needed to invoke this tool correctly: scope, ordering, time filter field, filter example, unsupported search, known error fallback, and pagination semantics are already in the schema. No critical behavioral information is missing for an agent to select and call it appropriately.

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?

Although the schema already provides 100% description coverage, the tool description adds crucial semantics beyond the schema: the time filter applies to lastModifiedDateTime, default sort is newest first, filter expressions like "contains(title,'x')" are supported, and the 'search' parameter is not supported by Graph v1.0. This materially improves the agent's ability to construct valid parameter combinations and avoid the search parameter pitfall.

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 starts with a specific verb and resource ('List OneNote pages across all personal notebooks') and immediately adds the distinguishing default ordering ('newest first'). It clearly differentiates from the many OneNote section/page siblings by emphasizing scope across notebooks, not sections or sites.

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 explicitly tells the agent when this tool is appropriate ('across all personal notebooks') and when it is not, including the fallback path ('then go notebook -> sections -> list-onenote-section-pages instead') for accounts hitting error 20266. It also explicitly warns that full-text 'search' is unsupported and directs toward filter usage instead, which prevents a common misuse.

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