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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the safety profile is covered. The description adds real value beyond that: the status enum (ok|degraded|down), the HTTP 503-only-when-down mapping, and that source/freshness metadata is returned.

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 health content is front-loaded and tight, but the trailing 'Units: ft, kt, s, F, mi; directions FROM' line is boilerplate that is irrelevant to a health endpoint and does not earn its place.

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 zero-required-param diagnostic tool with no output schema, the description covers the return shape well enough (status enum, HTTP behavior, metadata presence, detail expansion). Return-value specifics remain vague, but no output schema exists to offload them.

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% and the single nested param (detail, boolean) is undocumented in the schema. The description compensates by stating 'detail=true lists every source', which is exactly what an agent needs to choose a value.

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 names a specific resource (ingest worker heartbeat, feed-family staleness, government dataset status, GLM lightning) and a concrete verb (rolls up). It is clearly a health/diagnostic tool, though it never explicitly distinguishes itself from the closely related sibling get_source_status.

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?

'Check this before trusting no data from other tools' gives explicit, actionable when-to-use guidance and the detail=true note clarifies the expanded mode. It lacks any when-not guidance or a direct comparison to get_source_status/get_data_coverage, which are the nearest alternatives.

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