cipp_list_user_signin_logs

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

Annotations already establish readOnly/non-destructive, so the description's added context is what counts: one tenant and one user per call, the UPN→object-id resolution the upstream filter requires, and the license prerequisite. It also enumerates the returned fields and a summary block, which is valuable for a no-output-schema tool. Minor gap: no pagination/rate-limit behavior beyond the schema's top limit.

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?

Front-loaded with purpose and followed by return-content, identity handling, scope, license, and the alternative-tool routing. It is dense and the long field enumeration could be trimmed, but every clause carries information and nothing is buried.

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 compensates by describing the row content (time, app/resource, IP, location, result and error reason, CA policies, MFA requirement and auth steps, device, risk) plus a failure/IP/country summary. Combined with the tenant scope and license requirement, an agent has everything needed to call and interpret 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 100%, so baseline is 3, but the description adds meaning the schema does not: a UPN is resolved to an object id first because the upstream filter matches object ids only, and 'allTenants' is effectively unusable. That explains the behavioral cost of passing a UPN rather than a raw id.

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 and resource ('List one user's most recent interactive Entra ID sign-ins'), scopes the subject to a single user, and explicitly routes the tenant-wide case to a named alternative (ListSignIns). An agent can distinguish it from siblings like cipp_list_audit_logs or cipp_list_logs without opening schemas.

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?

Gives concrete selection conditions ('why can't this user sign in', 'was this account used from somewhere unexpected', 'did MFA/CA apply') plus an explicit exclusion for tenant-wide queries with the named sibling to use instead. It also surfaces the prerequisite (Entra ID P1/P2) which gates whether the tool is usable at all.

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