detect_login_loops

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 well: it discloses the KEYCLOAK_DEADLINE time bound (default 45s), that results may be partial with a 'PARTIAL RESULT' prefix, that counts become a lower bound, and the correct retry strategy. This is exactly the kind of non-obvious behavior an agent needs before calling.

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 the purpose, then a well-structured args list. The deadline paragraph is slightly long but every sentence (partial results, retry advice, trigger cause) earns its place. Minor verbosity only.

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 5-param detection tool with an output schema already covering return values, this description covers purpose, all parameters, time-bounding behavior, and failure handling. Nothing an agent needs to call it correctly is missing.

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 documents all five parameters: date formats (YYYY-MM-DD), defaults, the meaning of threshold/window_seconds, and 'Use 0 for all' for top. It fully fills the gap left by the schema.

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+resource+scope: 'Detect users with rapid repeated logins (possible redirect loops).' This is immediately distinguishable from siblings like spray_check and get_login_failures_by_ip, which target different attack patterns.

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?

Usage is implied by the detection description, and it gives good operational guidance ('Call again with a narrower window instead of retrying'), but it never explicitly says when to choose this over a sibling like spray_check or get_login_stats. No when-not or alternative routing is provided.

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