connection_health

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

Beyond readOnlyHint=true, the description discloses real behavior: results are in-memory with no round trip on the caller's thread, background probing is throttled to at most every few seconds, and notices are one-time messages above a supplied id (e.g. after a SAS session restart). This is genuinely non-obvious context an agent could not infer from 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?

The content is dense but the single run-on paragraph crams purpose, two parameter explanations, and a parenthetical aside ('the page came back online') together. The core answer (service reachability plus pending notices) is not front-loaded as a crisp summary, and the backtick-formatted fragments read like code comments rather than agent-facing prose.

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?

With no output schema, the description should convey the shape of the result, but it never says whether health is returned per service, as booleans or status strings, or how notices are packaged alongside it. The behavioral and parameter sides are reasonably covered, yet an agent cannot predict what it will receive.

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 carries the full burden, and it does document both parameters: probe's three modes and the meaning of after_notice as a watermark for one-time notices. It omits the stated defaults ('down', 0) and the exact accepted literal set is only loosely implied, but the semantics are far richer than the bare string/integer 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 opening clause states exactly what the tool answers: whether SingleStore and SAS Viya were reachable on the last calls, and that the answer comes from memory rather than a live round trip. It does not name any sibling (connection_test, sas_viya_test, connection_helios_ca) that would be the live-check alternative, so differentiation is left implicit.

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 meaning of each probe mode ('down', 'all', 'none') implies when to trigger a background recheck, which is useful usage-adjacent guidance. But there is no statement of when to prefer this cached snapshot over an active connectivity test, and no exclusions or prerequisites are given.

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