Find Facility

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

Annotations already declare readOnly/idempotent/closed-world, but the description adds substantial behavior beyond them: the dataset is a hand-compiled incomplete sample, an unknown county returns an empty list with a note rather than a guess, and it enumerates the return payload (county, facilities, note, emergency numbers, source label). This is exactly the kind of disclosure that prevents an agent from over-trusting the result.

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 purpose and trigger, then caveats, then return shape; nearly every clause carries new information. Slightly dense and the trailing 'Read-only.' repeats the readOnlyHint annotation, but overall efficient.

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?

Even though an output schema exists and return details are technically redundant, the description covers the one thing the schema cannot: the dataset's incompleteness and the empty-list-not-guess contract. Nothing an agent needs to call or interpret this tool correctly is missing.

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 100% and the schema already documents both the county examples and the level mapping (4/5/6/0). The description's level legend duplicates the schema text verbatim, adding no meaning beyond it, so the baseline 3 applies.

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 and resource ('Find sample public health facilities in a Kenyan county') plus the optional KEPH-level scoping. The domain is clearly disjoint from the sibling tools (contributions, maternal protocol, health rights), so an agent can route 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?

'Use when someone asks where to go for care' gives an explicit trigger, and the KMHFL caveat implicitly scopes it as a small sample rather than an authoritative lookup. No sibling alternative is named, but none is needed since the use cases don't overlap.

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