Log Anomaly Detection

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

Annotations already indicate readOnly, idempotent, non-destructive. The description adds behavioral detail: it compares logs against baselines and requires an external URL. This adds value beyond annotations without contradiction.

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 concise and front-loaded: first sentence defines the action, then explains methodology and constraints, then parameter list. Every sentence is essential, and it avoids extraneous information.

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?

Given the output schema exists, the description adequately covers input and behavior. It explains the core logic and prerequisites. Minor gaps (e.g., no mention of output format or error cases) are acceptable due to the presence of the output schema.

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 has 0% description coverage, but the description lists all three parameters (uuid, tenant, url) with short explanations of their roles. This compensates adequately, though more detail on format or constraints would be beneficial.

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 the tool detects anomalous log lines using LogJuicer ML-based analysis, comparing failed against successful builds. This specific verb+resource combination distinguishes it from sibling tools like get_build_failures or get_build_log.

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 provides context on when to use (for anomaly detection) and prerequisites (LOGJUICER_URL configuration). It implicitly differentiates from siblings via the unique functionality, but lacks explicit when-not-to-use or alternative tool references.

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