Проверка срочности по симптомам животного (кошка, собака, грызун, птица, рептилия): угроза жизни / к врачу сегодня / наблюдать. Таблица признаков подтверждена ветеринарными врачами. Это маршрутизация, не диагноз.
| Name | Required | Description | Default |
|---|---|---|---|
| species | No | Вид: кошка/собака/грызун/птица/рептилия (необязательно) | |
| symptoms | Yes | Что с животным, свободным текстом по-русски |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full transparency burden. It discloses the tool's purpose, its non-diagnostic nature, the urgency categories, and that the symptom table is veterinarian-confirmed. This is solid behavioral disclosure, though it does not explain what happens with unclear or missing symptoms.
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, information-dense sentences. The purpose and output categories are front-loaded, and the critical caveat ('not a diagnosis') is placed at the end without padding. Every sentence 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?
Despite having no output schema, the description explicitly names the three output categories, lists supported species, states the input format, and adds a veterinary-validated caveat. For a simple triage tool, this is complete enough for an agent to invoke it correctly and interpret results.
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 both parameters are already documented in the schema. The description adds the species list and the free-text nature of symptoms, but these largely repeat the schema descriptions rather than adding new meaning. 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?
The description states a specific action ('Проверка срочности') on a specific resource (animal symptoms) and defines the three possible outcomes: life-threatening / vet today / observe. It also distinguishes itself from diagnosis with 'Это маршрутизация, не диагноз', which separates it from sibling tools like ask_vet_kb.
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 description clearly implies when to use the tool: when an urgency assessment is needed based on symptoms. It also gives an explicit exclusion by stating it is routing, not diagnosis, which helps the agent avoid using it as a diagnostic tool. However, it does not name specific sibling tools or provide direct 'use X instead' guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct task: clinic lookup, slot availability, booking, prices, general health Q&A, food safety, and urgency triage. The health-related tools (ask_vet_kb, food_check, triage) have clearly separated purposes in their descriptions, so agent misselection is unlikely.
Most tools follow a verb_noun pattern (find_clinic, check_slots, book_visit, get_prices). food_check reverses the order and ask_vet_kb uses an abbreviation, creating minor inconsistencies, but the overall pattern is still readable and predictable.
Seven tools is well within the ideal range and each tool serves a necessary function in the pet-care workflow. The set is neither bloated nor too thin for a veterinary clinic assistant.
The main workflows are complete: clinic discovery, appointment booking, price lookup, and health/triage information are all covered. Missing appointment cancellation or modification is a minor gap but does not break the core service.