Ostrov retreat center

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

Annotations already establish readOnly/idempotent/non-destructive, but the description adds a genuinely new behavioral trait: the calculation neither persists nor contacts anyone. It also hints at the response shape ('complete, warnings and availabilityStatus'). It stops short of noting rate limits or exactly what a warning signifies.

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 with the key constraint front-loaded and no filler. The second sentence is terse and slightly cryptic ('Check complete, warnings and availabilityStatus'), but nothing is wasted.

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 tool with a highly complex two-branch plan schema and no output schema, the description is only partially adequate. It helpfully names response fields (complete, warnings, availabilityStatus) but never explains the two plan variants or what the top-level kind values mean, which an agent needs to call it correctly.

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?

Top-level schema description coverage is 0% for kind, plan, and catalogVersion, and the description explains none of them - not the kind enum values, not the two plan variants, not catalogVersion's role. The nested field descriptions do the real work, so the description adds nothing here despite the coverage gap.

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 verb 'Calculate' restates the tool name and the resource (quote/price) is only implied by the name, not stated in the text. The added 'without saving or contacting anyone' scopes it as a dry-run, which is useful, but it never says what is being quoted or for whom. Siblings like suggest_group and get_catalog are not differentiated.

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 'without saving or contacting anyone' implies the right context (preview before committing) but never names an alternative or a when-not condition. No sibling tool is referenced, so the agent must infer that this is the non-persisting counterpart to whatever saves a booking.

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, openWorld and non-destructive behavior, so the safety profile is covered. The description adds one genuinely behavioral caveat beyond that (absence of activity is not evidence of availability), but says nothing about scope limits, timezone handling, or result size for a date-range query.

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?

It is short and contains no padding, and the caveat it does state is front-loaded. However, the terseness comes at the cost of the essential content, so it reads as under-specification rather than disciplined concision.

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 no output schema, no parameter documentation, and no annotation coverage of return content, the description is the only source of behavioral guidance and it provides a single caveat. An agent cannot tell what a calendar entry looks like or what the range bounds mean from this definition.

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% for both required parameters, so the description carries the full burden of explaining start and end. It supplies no information about them — no range semantics, no inclusivity, no timezone — leaving the agent to infer everything from the date pattern alone.

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 name get_calendar supplies the verb+resource, but the description never states what the tool does. 'Confirmed public activity' is a fragmentary characterization of the returned content rather than a purpose statement, and it does not differentiate this tool from siblings like get_events or get_center.

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 clause 'empty dates do not mean availability' is a useful interpretation caveat, but there is no explicit when-to-use guidance, no prerequisite conditions, and no routing to an alternative sibling when the agent needs a different view of the data.

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 readOnly, idempotent, open-world, non-destructive. The description adds genuinely new behavioral context beyond that: the data reflects a 'current' tariff version and prices must not be cached as permanent knowledge, telling the agent the payload is time-sensitive. It stops short of describing the shape or size of the returned data.

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 with no filler, and the subject of the catalog is front-loaded. The first sentence is a fragment rather than a complete statement, which slightly weakens the front-loading.

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 read tool with no output schema, the description is minimally adequate: it hints at contents ('resources and rules') but never says what a returned catalog actually contains or how to consume it. The freshness caveat helps, but an agent still has to discover the response shape by calling it.

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 per the rubric the baseline is 4. The description has no parameter behavior to explain and correctly adds none.

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 names the resource domain (tariff version, resources, rules) but is a noun fragment with no verb, so it never states that it retrieves/returns the catalog. An agent can partially distinguish it from calculate_quote or get_events from the subject matter, but the action itself is only implied.

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?

There is no when-to-use guidance and no mention of alternatives, despite calculate_quote being an obvious sibling that consumes tariff data. The only directive is a caching caveat, which is operational advice rather than selection guidance.

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 the full safety profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower. The word 'public' hints that the data is not access-restricted, which is a small addition, but the description says nothing about freshness, caching, or rate behavior beyond what annotations provide.

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?

A single short sentence with no filler or redundancy, and the key concept ('public location and contact information') leads immediately. It is efficient, though efficiency here comes partly from under-specification rather than tight editing.

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 no output schema and no parameters, the description carries the burden of explaining what comes back, and it does not: it never says whether the response is an address, phone numbers, hours, coordinates, or all of these, nor what 'center' refers to. For a zero-arg lookup with no structured return documentation, this is too thin.

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 per the baseline a 4 applies; there is nothing for the description to disambiguate. No parameter-level meaning is needed or missing.

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 is a bare noun phrase, 'Public location and contact information,' with no verb and no indication of what entity the center is or how it differs from siblings like get_catalog, get_events, or get_objects. It conveys the rough subject matter but is closer to a label than a statement of what the tool does.

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?

There is no when-to-use guidance, no mention of when not to use it, and no routing to or away from any sibling tool. The agent is left to infer that this is the thing to call for center details purely from the name.

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, openWorld and non-destructive, so the safety profile is covered. The description adds only that the dataset contains public programs and labeled demo data, without saying what a call returns, whether results are filtered, or any rate/scope limits.

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?

It is a single short sentence with no filler, which is appropriately sized. However, it is an unstructured fragment that leads with data provenance instead of the tool's function, so it is not front-loaded on what the agent needs.

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 no parameters and no output schema, the description is the only place that can say what comes back, and it never does; it also omits any note on how 'public' vs 'demo' data affects results. For a listing tool this leaves the agent guessing at the return shape.

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 schema takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter meaning is lost.

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 text never states a verb or that it returns events; 'Public programs and labeled demo data' describes the content domain rather than the action. Against siblings like get_calendar and get_catalog there is no differentiation of scope.

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?

'Contact the organizer to ask about joining' is advice about the underlying activity, not about when an agent should call this tool versus get_calendar or get_catalog. No trigger condition, no exclusions, no alternative named.

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, openWorld, idempotent and non-destructive, so the safety profile is covered. The description adds one genuinely useful behavioral caveat – that availability data carries 'no guarantee of open places' – which is freshness/accuracy context the annotations do not convey. It stops short of anything else, such as scope or staleness timing.

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?

A single short sentence with no padding, so nothing wastes the agent's attention. It reads as a noun-phrase fragment rather than a stated action, which slightly weakens the front-loading but keeps it tight.

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 no output schema, no parameters, and no annotations explaining return shape, the description should do more to explain what a caller receives and how it relates to siblings like get_catalog. The availability caveat is helpful, but an agent still cannot confidently predict the response.

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 and there is no parameter behavior the description could usefully add. Schema coverage is 100% with an empty property set, so nothing is missing.

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 gestures at the content ('public resource descriptions and availability rules') but never defines what an 'object' actually is in this domain, so the verb+resource pairing stays vague. It also gives no differentiation from siblings like get_catalog or get_center, which could plausibly return overlapping data.

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?

There is no when-to-use guidance, no prerequisites, and no mention of any alternative tool. With six sibling tools available, the agent is left to guess whether this is the right entry point.

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 and openWorldHint, so the safety profile is covered. The description adds real behavioral context by clarifying this is advisory/selection output rather than an availability verification, but it says nothing about what a 'suggestion' contains, whether results are deterministic, or how policyVersion/catalogue versioning affects output.

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?

A single, front-loaded sentence with no filler; the negative clarification is attached efficiently to the main clause. It is arguably too terse for a tool with a deeply nested required payload, but no sentence is wasted.

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 complex, nested-required-parameter tool with no output schema, the description omits what the returned suggestion looks like, whether catalogVersion is mandatory for valid results, and any prerequisite workflow. The annotations cover only the read-only/idempotent profile, so this one sentence does not carry the burden the tool's complexity demands.

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?

None of the three top-level parameters (kind, plan, catalogVersion) are mentioned in the description, and top-level schema description coverage is effectively 0% — only deep nested fields carry their own descriptions. The description does not compensate by explaining the plan payload shape or the meaning of catalogVersion, leaving the agent to mine the nested 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 ('suggest') and resource ('room/program selection for the ordinary group tariff'), which is concrete and matches the const 'group' kind and policyVersion in the schema. It does not name a specific sibling it competes with, so an agent must still infer its place among calculate_quote/get_calendar, but the purpose itself is unambiguous.

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 clause 'not an availability check' is a useful negative signal that steers the agent away from treating this as a calendar/availability query, which implies when to use it. However, no positive alternative or prerequisite is named (e.g., 'use calculate_quote for pricing' or 'requires a prior get_catalog call'), so usage is only implied.

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