backend_health_rca

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

With no annotations, the description carries the full burden. It discloses that it is a read operation ('[READ]'), mentions live pulling vs. injected data, and describes the classification and action output. While it doesn't discuss error handling or side effects, it is a thorough disclosure for a read-only tool.

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 and front-loaded: a one-line summary, then a detailed explanation, followed by an Args section and a Returns section. Every sentence adds value, and the length is justified given the lack of schema descriptions and output schema.

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?

The tool is complex with 3 optional params, no annotations, and no output schema. The description compensates fully by explaining the return dict structure, parameter semantics, and behavior. It is complete enough to invoke correctly without additional context.

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 description coverage is 0%, so the description must compensate. It does so excellently by explaining each parameter: service as an optional filter, upstreams as injected rows with a specific format and semantics (skips live pull), and target as a proxy target name with default behavior. This adds substantial meaning beyond the bare 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?

The description clearly states the tool's purpose: 'Down upstreams grouped per service, each mapped to cause + action.' It uses specific verbs (pulls, groups, classifies) and resource (server-level upstream health), and distinguishes itself as the 'flagship availability RCA' among sibling diagnostic tools.

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 clear usage context: it is for availability RCA, and explains two modes—pass 'upstreams' for pure analysis or a target to pull live. It doesn't explicitly name alternatives or exclusions, but the 'flagship' positioning implies primary use for this scenario.

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