K-Pet Info

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

Annotations already declare read-only, idempotent, closed-world, non-destructive, so the safety profile is covered; the description adds the data provenance (Merck Veterinary Manual dose thresholds) and the output behavior (emergency level derived from weight + amount). It stops short of saying what is returned when weight or amount is omitted, which is the one behavioral unknown left.

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 action and substance list, followed by two short caveat sentences that each carry real signal. The parenthetical substance list is long but earns its place by defining scope; otherwise there is no filler.

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, the description does enough: it names the two outputs (toxicity verdict and emergency level) and the caveats a safety-sensitive agent must convey. Slightly more on partial-input behavior (substance only vs. substance + weight) would close the remaining gap.

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 every parameter including lang and variant is already documented in the schema. The description reinforces weight and amount as the inputs that drive emergency-level computation but adds no format or fallback rules beyond that. Baseline 3 applies when the schema does the heavy lifting.

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 ('Check whether something a dog or cat ate is toxic') and enumerates the covered substances plus the dose-threshold emergency-level output. It is unmistakable against siblings like find_vets or get_breed, which share no domain function.

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?

Sets a clear context (pet ingestion triage) and two explicit boundaries: unlisted substances are NOT confirmed safe, and the tool is a triage aid, not a diagnosis. It doesn't name an alternative tool or say when not to call it, but the sibling set is unrelated so the gap is minor.

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, closed-world, non-destructive behavior. The description adds meaningful context beyond that: the data source is the Korea Tourism Organization, results are Korea-only, data is in Korean, and listings include pet rules. It still does not cover pagination or return-shape behavior, which keeps it from a 5.

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?

The description is a single front-loaded sentence followed by two short constraints. Every clause adds useful scoping information with no repetition or waste.

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 read-only search tool with annotations and no output schema, the description covers the essential scope, source, language, and content type. It could say more about pagination or result fields, but an agent has enough to invoke 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?

Schema coverage is 50%, with sido and sigungu documented but type and limit left undocumented in the schema. The description maps the type categories to human-readable concepts, but it does not explain limit or the sido/sigungu relationship, so it only partially compensates for the schema 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 description states a specific resource set—pet-friendly stays, restaurants/cafes, attractions, leisure and culture spots—within a South Korean province, and adds source and language constraints. It is clearly distinguishable from siblings like find_vets or find_rescue_animals without needing their schemas.

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?

It gives a clear usage boundary: Korea only, with data in Korean. That tells the agent when the tool is applicable versus not, though it does not explicitly name alternatives or when to prefer another sibling tool.

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, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the APQA source, daily sync freshness, and the sort order. It stops short of describing result volume 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?

A single dense sentence with a parenthetical for provenance; scope, freshness, ordering and language all front-loaded with no filler. Every clause carries information.

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 only 50% parameter coverage, the description does well on source, freshness, sort order and locale, but never sketches what a record contains (breed, notice dates, shelter contact) or how many results come back. That is a minor but real gap for a discovery tool.

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 50% – sido and sigungu are documented with examples, and kind is an enum, so structured data does much of the work. The description only implicitly maps 'dogs, cats and other' to the kind enum and 'Korea only' to the geographic filters; it says nothing about limit or its default/max of 20/50.

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 resource (dogs, cats and other animals in public notice at South Korean shelters), the data source, and the ordering (soonest notice end first). This is clearly distinguishable from the sibling tools (find_vets, find_pet_travel, get_breed, check_toxic_food) 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?

'Korea only; data in Korean' gives useful scoping constraints, but there is no explicit when-to-use vs. when-not, and no sibling is named as an alternative (e.g., get_breed for breed details, find_vets for care). Usage is implied by the domain 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 declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower. The description adds real value beyond that: the authoritative source, that names/addresses are Korean-only, and that opening hours are NOT included — a genuine limitation that prevents wrong assumptions.

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 dense sentences: the capability and return fields are front-loaded, followed by the usage caveats. Zero filler, every clause 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?

No output schema exists, and the description compensates by listing returned fields (address, phone, 24-hour flag). The only omissions are result limit/pagination behavior and how multiple matches are ranked — minor against an otherwise complete definition for a simple lookup tool.

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 75%, so most parameters are already documented in structured fields. The description adds context for 'region' (district-level, must be Korean) but says nothing about 'sido', 'limit', or the emergency_only flag mechanics beyond the schema's own text. Baseline 3 is appropriate.

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+resource (open veterinary clinics in a Korean si/gun/gu district), names the data source (Ministry of the Interior licensing data), and enumerates the returned fields. An agent can tell exactly what this tool yields 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?

Clear usage context: Korea only, district-level granularity, Korean-language queries. No explicit comparison to siblings (check_toxic_food, find_pet_travel, etc.), but those are clearly different domains, so routing ambiguity is low. Scope exclusions ('no opening hours') are stated, though the alternative for hours lookup isn't given.

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=false, so the safety profile is covered. The description adds genuine behavioral context: matching works across Korean names, English names and slugs, output language is selectable, and the returned profile includes a suitability guide — details not derivable from annotations. It omits not-found or ambiguity behavior (e.g., does 'maltese' resolve to cat or dog without species?), which keeps it below a 5.

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 dense sentence pair with the resource front-loaded and examples at the end. The long enumeration of profile fields is justified because there is no output schema, though it reads as a run-on list rather than a structured one.

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, the description correctly carries the return-value burden by listing the profile fields and the language behavior. The remaining gap is the undocumented 'species' parameter and no guidance on name ambiguity or unknown breeds, which matters for a lookup tool with three parameters.

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?

With 67% schema coverage, the schema already documents 'breed' (Korean/English name or slug) and 'lang'. The description reinforces and illustrates the breed matching with concrete examples ('maltese', '말티즈', 'golden retriever'), which is meaning beyond the schema. However, the 'species' parameter is neither described in the schema nor mentioned in the description, leaving the agent to guess whether it disambiguates overlapping dog/cat breed names.

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-object-resource combination up front: returns a profile of a dog or cat breed. The description enumerates exactly what the profile contains (size, weight, lifespan, temperament, health issues, feeding note, suitability guide), so an agent knows this is not a search or a list tool like the sibling tools find_vets or find_rescue_animals.

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 usage context is implied: this tool looks up breed facts by name, which none of the siblings do (toxic food, travel, rescue, vets). There is no explicit "use this when…" statement, no exclusion, and no mention of what happens when the breed is unknown or ambiguous, so the agent must infer the boundaries.

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