login_failure_rca

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

With no annotations, the description carries full responsibility. It discloses the '[READ]' nature, the return behavior including 'feedTruncated' and lower-bound counts, and that findings include numbers, cause, and action. It does not cover all possible side effects or prerequisites, but for a read-only analysis tool it is quite transparent.

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?

The description is well-structured: a succinct purpose line, a clear args list, and a crucial return-value caveat. No redundant or filler sentences; every sentence earns its place.

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?

For a tool with no output schema and no annotations, the description covers purpose, parameters, and key return behavior (feedTruncated). It does not detail the exact structure of findings but indicates each includes numbers, cause, and action. This is sufficient for an agent to select and invoke the tool correctly, though more detail on return format could push it to 5.

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 explain parameters. It does so effectively: window_minutes as trailing window, max_events as event pull count, target as IdP name with omit-to-use-default semantics. This adds crucial meaning beyond the schema's types and defaults.

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 clearly states it performs RCA over the failed-auth feed and enumerates specific categories (brute-force, misconfigured client, expired-credential storm, lockout storm), distinguishing it from sibling tools like login_events or client_misconfig_audit. The verb 'RCA' and the resource 'failed-auth feed' are specific.

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 clearly sets context for when to use it (RCA of failed logins) but does not explicitly mention alternatives or exclusion cases. It lacks explicit when-not-to-use guidance, but the context is sufficiently clear.

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