Document Insights

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds provenance (Graph item insights) and a default mode, but says nothing about authentication requirements, result freshness/latency, or how many insights Graph actually surfaces — modest added value over the annotations.

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 short sentences, front-loaded with what is returned before the use cases, and no filler or redundancy. Every sentence contributes to selecting or interpreting the tool.

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 no output schema, the description should hint at the shape of returned document entries; it only says 'documents' without indicating whether titles, URLs, senders, or timestamps come back. For a two-parameter convenience tool this is adequate but leaves a real gap for an agent forming a response.

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 100%, so both parameters (kind, count) are already fully documented including enum meanings and the 1-50 default. The description only restates the default mode, adding no syntax or behavioral detail beyond the schema — the baseline 3 applies.

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 states a specific resource (documents recently worked with or shared) and its data source (Microsoft Graph item insights), with concrete use-case phrasing ('what was I working on'). It implicitly distinguishes itself from filename-based retrieval ('without knowing a filename'), pointing away from ms_files/ms_search, though it never names those siblings.

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 clear context for when this tool fits: recall-oriented questions where the filename is unknown, and it notes the default behavior ('Defaults to recently used'). No explicit exclusion or naming of alternative tools, so it falls short of the top band.

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