CareOpenly - Find Senior Living Communities

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

Goes well beyond the readOnly/idempotent annotations: it discloses that name lookup reports unresolved ambiguity, that records carry sources and dates, that missing fields stay unavailable, that prices are observations rather than quotes, that coverage records do not determine individual benefits, and that results carry a request-information link. These are data-semantics caveats annotations cannot express.

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 core read-only scope, and most sentences carry real caveats (prices vs. quotes, coverage vs. benefits) that an agent needs. The single dense block is longer than necessary and the closing link sentence adds little, but nothing is redundant with the annotations.

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 an output schema present, return values need no explanation, and the description covers auth, data provenance, and semantic caveats well. The one gap is that it never states the name-or-publicId requirement implied by the all-optional parameter set.

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 100%, so the baseline is 3; the description adds value by mapping the content categories (prices, reviews, amenities, services, coverage, inspections) to the include enum and clarifying which summaries are always returned. It does not state that at least one of name/publicId is needed, leaving the zero-required-parameter case to the 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?

States a specific verb and resource ('details for a named senior living facility or its stable publicId') and enumerates exactly what content is covered (care types, prices, floor plans, reviews, coverage, licensing, inspections). The distinction from the sibling search_facilities is only implied by 'named facility' vs. a listing/search, so it stops short of a 5.

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?

'Public, read-only ... without a CareOpenly account' plus 'Relevant to questions about a specific community's care types, published starting and care-specific prices...' gives clear conditions for use. It never names search_facilities as the alternative for discovery or states exclusions, so the routing guidance is implicit rather than explicit.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint, so safety is covered structurally. The description adds genuinely useful non-annotated context: no authentication/account needed, and the default-radius rule (exact city inventory for city/ZIP, 15 miles for landmarks), which materially affects how the agent should call it.

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?

Four sentences, each doing distinct work: capability, relevance, geo-default rules, and result content. Front-loaded with the core verb and resource; nothing is padded, though the final results sentence is partly redundant with the output schema.

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 7-parameter search tool with an output schema and full annotation coverage, the description supplies what's missing: account requirements, radius defaults, and care-type coverage. Return-value details are already in the output schema, so brevity there is appropriate; the only gap is the absence of explicit sibling routing.

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 71%, so the schema already documents most parameters including radius and coordinate semantics. The description nonetheless adds meaning by enumerating the resolvable destination forms (city, ZIP, hospital, neighborhood, landmark, verified coordinates) and by clarifying the radius default behavior in prose, reducing ambiguity for the required destination parameter.

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 ('Public, read-only search for senior living communities') plus the full set of location inputs it accepts, so the agent knows exactly what this tool does. Mentioning that results carry 'stable facility IDs' implicitly routes detail lookups to the sibling get_facility, giving de facto sibling differentiation.

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?

Explicitly frames the questions this tool answers (assisted living, memory care, independent living, 55+, other care types in or near a place) and states that no account is required, which is clear usage context. It does not explicitly name get_facility as the follow-up alternative for a single known facility, so routing guidance stops short of full when/when-not coverage.

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