set_sensitivity_labels

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

With no annotations, the description carries the full behavioral burden, and it does add real value: dry_run is explained as 'validate permissions without applying labels' and redact_names as log redaction. However, it omits whether labels are reversible, what permissions are actually required (admin_scopes is mentioned only as an arg), and whether dry_run defaults to True — schema shows default true, meaning an agent could believe labels were applied when nothing happened.

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?

Purpose and trigger conditions are front-loaded, then Args/Returns blocks; nothing is wasted. The Args section inherently restates parameter names, and the Returns block is partly redundant given an output schema exists, but the utility description itself is tight.

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?

An output schema exists so return-value detail is not required, and the description still summarizes the shape (updated items, failed items, compliance status). For a 6-parameter mutation tool with zero annotations, it covers intent, params, dry-run safety, and error surface adequately; the remaining gap is permission/irreversibility context.

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% (only titles like 'Label Id'), so the description must compensate, and it documents all six parameters with meaning beyond the schema: item dict shape with a concrete example, label_id as a Purview GUID, label_name as display name, admin_scopes as optional authorization scopes, and the semantics of redact_names and dry_run. It does not list valid label_name values or item type enumerations, which keeps it at 4.

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 first sentence states a specific verb and resource ('Apply Microsoft Purview information protection sensitivity labels to items'), which is unambiguous and actionable. It does not name or contrast with any sibling tool, but no sibling in the list performs label application, so differentiation is implicit 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?

'Use this tool when the user asks to: classify or protect Power BI items... / set Purview sensitivity labels' gives explicit trigger conditions tied to user intent. It stops short of stating when NOT to use it or pointing to an alternative for adjacent tasks (e.g. RLS/roles via setup_rls_and_roles), so it earns 4 rather than 5.

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