sns_find_institutions

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

With no annotations, the description carries the full burden and does so: it enumerates each returned field, explains that `stats_entity` is a ULS/group-level name rather than a building-level one, and discloses a non-obvious quirk ('Without `query`, umbrella ULS entries are skipped (they duplicate a hospital's location)'). It also warns about the absence of live wait times, preventing a likely misuse.

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, then usage, then return shape, then args — a logical order with no filler sentences. It is on the long side (~200 words): the important 'umbrella ULS skipped without query' caveat is buried inside the lat/lon sub-bullet rather than surfaced earlier.

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 5-param, zero-annotation, zero-schema-documentation tool, the description supplies everything an agent needs to select and call it correctly, plus the hand-off contract to the three stats tools. An output schema exists, so return values need not be re-explained, and the field enumeration is justified anyway because it clarifies `stats_entity`.

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%, so the description must compensate and it does for all five params: `query` is accent-insensitive with examples, `lat`/`lon` are WGS84 and sort by distance with a sample coordinate, `emergency_only` filters to emergency-reporting sites, and `limit` gives default (10) and max (50). It also explains the interaction between `lat/lon` and `query`, which the schema cannot express.

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?

Opens with a specific verb and resource: 'Find SNS hospitals / local health units (ULS) by name, or the nearest ones to a coordinate.' It explicitly separates this lookup role from the statistics siblings (sns_emergency_stats, sns_surgery_wait_stats, sns_consultation_wait_stats) that consume its `stats_entity` output.

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?

States a clear trigger ('Use this first when the user names a hospital or a place') with two concrete example queries, defines the follow-up step (pass `stats_entity` to the stats tools), and gives an explicit when-not with a redirect ('This list does NOT contain live waiting times; for live emergency waits send the user to https://tempos.min-saude.pt').

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