Intelligence Engine Status

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is established. The description adds value by disclosing the tool is a status/health read that returns state rather than data, and enumerates the derived statuses (ok/stale/empty) and pipeline metadata that compose the response. This complements rather than duplicates the annotations.

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?

Two sentences, zero filler. The first sentence densely enumerates the return payload using semicolon-separated clauses, and the second gives one actionable directive. Every word earns its place with no rhetorical padding.

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 parameterless, read-only status tool with no nested objects, an output schema, and full annotations, the description is complete. It not only lists the payload categories but also the derived status vocabulary and the use-case context. There is an output schema to define return structure, so the description need not duplicate field details.

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?

The tool has zero parameters, so the baseline is 4 per the rubric. The description appropriately focuses on describing what the tool returns instead of parameter usage, which is the correct approach for a parameterless tool. No parameter documentation is needed.

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 opens with a specific interrogative about pipeline health and enumerates exactly what is covered: per-engine row counts, last-compute times, ok/stale/empty status, nightly graph pipeline progress/stage/degraded flag, recent failures, and latest AUC eval. It clearly distinguishes from siblings like health and get_platform_stats by specifying the concrete data points returned.

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 final sentence gives explicit guidance: 'Check this before reasoning over correlation output if freshness matters.' This is a clear when-to-use directive tied to a specific downstream workflow (correlation reasoning). Though it does not name alternative tools, it provides actionable context for when this check is warranted.

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