health_check

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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses that it authenticates once using a cached session, that it is lightweight and performs no problem/item scanning, and it enumerates the exact return keys including degraded/error extras (detail, categories_error, read_only_error). That is unusually rich behavioral disclosure for a health probe.

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?

Front-loaded with the one-line purpose, then usage triggers, then the behavioral qualifier. The return-keys paragraph is dense and long, but it is justified because no output schema exists; a slightly tighter enumeration would read better without losing information.

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 and no parameters, the description must carry the full burden of explaining the response contract — and it does, listing all stable keys plus the conditional error keys. Combined with the call-site guidance, an agent has everything needed to invoke and interpret this tool.

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 takes zero parameters, so the baseline is 4; there is nothing for the description to clarify or compensate for. It correctly adds no parameter prose and instead spends its budget on behavior and return shape.

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?

States a specific verb set and resource: report server version, Zabbix connectivity, and configured categories. The scope is further sharpened by explicitly contrasting with sibling tools ('it does NOT scan problems or items'), so an agent can tell it apart from get_problems/get_hosts without opening a schema.

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?

Gives explicit when-to-use triggers ('at session start', 'after a tool-call timeout') and the conditions checked by the call (MCP up, version, backend reachable and authenticated, categories loaded). It also states what the tool deliberately does not do, leaving no ambiguity about routing.

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