signin_failure_stats

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

With no annotations, the description carries the full burden and does so thoroughly: read-only, required permission (AuditLog.Read.All) or azure-cli role (Reports Reader), a 45 s ENTRAADM_DEADLINE budget, and the crucial caveat that Graph can't filter server-side so results are a client-side sample, with `capped=true` marking lower-bound counts. This is exactly the behavioral disclosure an agent needs.

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-loads the core purpose well, but the middle paragraphs get verbose and partly promotional ('This mirrors the KeyCloak-side spray detection this fleet already relies on; neither the official Microsoft MCP Server for Enterprise nor Graph itself offers this aggregation'), which does not help an agent decide or call correctly.

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?

Despite having no output schema, the description enumerates the return shape (four views plus `spray_suspects`), explains the `capped` flag semantics, and covers auth/permission requirements and time-budget behavior. An agent has everything needed to invoke 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 0%, so the description must compensate, and it does: `hours` is documented as clamped to [1,720] and `max_pages` as a page budget tied to capping. It gives the default of max_pages only by env-var reference rather than a concrete number, a minor gap.

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 precise verb and resource — tenant-wide aggregation of failed sign-ins into four named views — and explicitly contrasts itself with the per-event `signin_logs` it borrows annotations from. The scope (tenant-wide, failure-only, grouped) is unmistakable from the sibling set.

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?

Explains the core use case (detecting low-and-slow spray that per-account lockout misses) and gives actionable tuning guidance: 'narrow hours for a full count.' It references `signin_logs` for per-event detail, but stops short of an explicit 'use this instead of X when Y' routing statement for the other siblings.

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