endpoint_health_score

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

With no annotations, the description fully discloses behavior: it is a read operation that works on injected data, deduces baselines from fleet majority if baseline is omitted, and cites deductions in reasons. All behavioral traits are 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 with a summary, detailed explanation, Args section, return format, and example. It is slightly verbose but every part adds value. The structure is clear and front-loaded.

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?

Despite having no output schema, the description fully specifies the return dict structure (endpointsEvaluated, baseline, summary, worst) and notes the note field. For a tool with moderate complexity and no annotations, the description covers all necessary 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 input schema has 0% description coverage, but the description compensates by explaining each parameter: endpoints are required injected rows, stale_hours has a default of 24, and baseline is an optional object with defaults derived from the fleet. This adds crucial meaning beyond 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?

The description clearly states it computes a composite per-endpoint health score (0-100), sorting worst first. It addresses a specific need ('which endpoints are worst?') and distinguishes from sibling tools like endpoint_list (which lists endpoints but does not score).

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 explains that the tool analyzes injected inventory rows and does not connect live, implying it should be used after fetching data via endpoint_list. It does not explicitly mention when not to use or contrast with alternatives like patch_compliance, but the context is clear.

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