lt_health

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds genuinely new behavior: probes are not cached, so the call yields fresh state without polluting or reading stale cache. It also decodes the status taxonomy, notably that 'degraded' means plain reads work but filtered queries fail — context that cannot be inferred 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?

Front-loaded with the purpose, then the trigger, then the return shape — a sensible order with no filler. The 'Returns:' block slightly restates what the output schema already declares, a minor redundancy but it does add the semantic gloss on status values.

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-parameter diagnostic tool with a real output schema, the description supplies exactly the missing pieces: when to invoke it, that probes bypass the cache, and how to interpret the three status values. Nothing an agent needs in order to call or interpret it is absent.

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 disambiguate. It correctly avoids spending text on nonexistent inputs.

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 diagnostic verb-object pair: check whether data.gov.lt answers and how the local cache looks. This is clearly distinct from the retrieval-oriented siblings (lt_search, lt_get_act, etc.), which an agent can tell apart without opening any 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 an explicit trigger condition: call it when a tool returns upstream_error or served_from_cache=true, and importantly 'before concluding anything from a failure.' This is actionable routing guidance rather than implied usage.

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