Kovante: Senior care

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description doesn't need to. It adds real context beyond them: output preserves input order, all entries share the same field set, and no ranking or score is produced — which prevents an agent from misreading the result as ordered by quality.

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?

One sentence, front-loaded with the action and scope, closing with the key exclusion ('no score or ranking'). Nothing redundant.

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 format needn't be explained; the description covers arity, ordering, field parity, and the non-ranking guarantee. Only minor gaps remain, such as behavior for unknown or duplicate facility identifiers.

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 carries the burden for the single facilities parameter. It supplies the min/max count and, importantly, the semantic that input order determines output order — meaning the schema's minItems/maxItems alone cannot convey.

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 (put facilities side by side), the exact arity (2 to 4), and the scope (same public record fields, no ranking). This clearly separates it from get_facility (single) and search_facilities (finding), so an agent can pick it without opening the 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?

The phrase 'No score or ranking' implies when this is preferable to a ranked search, but no sibling tool is named and no precondition (e.g. valid facility IDs, existence checks) is given. Usage is inferable rather than stated.

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 establish read-only, idempotent, non-destructive behavior. The description adds useful scope by listing what the public record contains and the caveat that phone is shown only where the page has one.

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?

Two tight sentences with no waste, front-loading the resource and record contents before the input instruction.

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?

Complete for a single-record lookup: input form is clear, annotations cover safety, and an output schema exists so return-value structure need not be restated.

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%, so the parameter is already well documented. The description adds meaningful provenance by saying the id can come from search_facilities, beyond the schema's format examples.

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 record of one facility') and enumerates the record fields. It is clearly distinguishable from search_facilities because it retrieves a single facility by address or id.

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?

Explains that the caller should provide a Kovante address or an id from search_facilities, giving clear usage context. It does not explicitly state when not to use it or name alternatives beyond the id source.

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 readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds that the content is advisory phone questions rather than factual record data, which is genuinely useful framing, but it says nothing about volume, structure, or whether questions vary by care type.

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?

Two short sentences, purpose front-loaded, no filler. Every clause carries information about what is returned and why it matters.

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?

Single enum parameter plus an output schema means the description only needs to convey intent, which it does. Minor gap: no hint about how many questions or whether the caller should pass results through to the user verbatim.

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 0%, but there is only one parameter and its enum fully enumerates the allowed values. The description's 'for a care type' restates the parameter name without adding format or selection guidance, so it neither compensates nor harms.

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 specifically that it returns suggested phone questions for a given care type, and that these are things the public record doesn't answer — enough to separate it from get_facility/search_facilities which return record data. The verb is soft ('suggests asking') but the resource is concrete.

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?

The phrase 'The public record does not answer these' implies the use case: call this when facility record data is insufficient. However, it never explicitly says when to use it versus compare or get_facility, and gives no guidance on chaining it after a facility lookup.

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, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context: the records come from state and Medicare public licensing data, result ordering mirrors the kovante.com search, and each result carries a link to the full record. It stops short of disclosure about the hard result cap or pagination behavior.

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?

Three tight sentences with the core capability front-loaded and no filler. The closing sentence about linking to Kovante records is slightly promotional but does convey a usable follow-up affordance, so it earns its place.

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?

An output schema exists, so return-value explanation is not required, and the data-source and ordering notes add real value. Still, for a 5-parameter search with only 40% schema coverage, the description leaves the budget filter, radius behavior and the 10-result cap unexplained, and never addresses what happens when a place cannot be resolved.

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 only 40%, so the description is expected to compensate, but it covers only the place input (town/county/ZIP) and partially the care types — omitting 'hospice', which is a valid enum value in the schema. The limit, radius_miles and max_monthly_budget parameters receive no explanation at all, and the 'modeled estimate' comparison for budget is left entirely 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?

The description opens with a specific verb and resource ('Find licensed nursing homes, assisted living and memory care'), scopes it geographically (US town, county or ZIP) and names the data provenance (state and Medicare public records). Combined with the title and sibling set, an agent can distinguish this directory search from get_facility (single record) and compare 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?

Usage context is implied by 'near a US town, county or ZIP' and by the note that every home links to its full record, which hints at a follow-up get_facility call. However, there is no explicit when-to-use/when-not guidance and no mention of the compare or questions_to_ask siblings, so routing still requires inference.

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