GPT, Claude, Gemini, DeepSeek, Grok, Qwen and GLM through one API key. Pay per token.
Scored across 4 tools
Each tool has a clearly distinct purpose: text generation, image generation, model listing, and balance checking. There is no functional overlap or ambiguity in selecting the right tool.
Three tools follow a verb_noun pattern (ask_model, generate_image, list_models), while 'balance' is a single noun. The deviation is minor and the naming remains predictable and readable.
Four tools adequately cover the core Store API actions—querying models, generating images, listing models, and checking balance. The count is well-scoped with no redundancy or bloat.
The core surface is well covered, including model discovery, text generation, image generation, and account balance. Minor non-essential gaps like usage history or streaming are absent but not critical for typical workflows.
Ask any model from the Store API catalog — GPT, Claude, Gemini, DeepSeek, Grok, Qwen, GLM — and get the answer as text. Lets you consult a second model from inside the current chat. — Задать вопрос любой модели каталога и получить ответ текстом.
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | Model slug, e.g. openai/gpt-6-sol or anthropic/claude-sonnet-5. Get the list from list_models | |
| prompt | Yes | Question or task for the model | |
| system | No | System instruction, optional | |
| max_tokens | No | Answer length limit, 1024 by default |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral burden. It discloses that the result is text and that an external catalog model is consulted, but it does not mention potential costs, balance consumption, latency, errors, or other side effects despite the sibling tool balance hinting at monetary implications.
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 core purpose is front-loaded and expressed in one clear sentence, with a brief context sentence afterward. The Russian translation adds redundant length, but the overall description is short and scannable.
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 moderately simple tool with fully documented parameters, the description covers what the tool does, what it returns, and when it is useful. Some behavioral details like cost or failure modes are absent, but the schema plus this description are sufficient for correct invocation.
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 schema already documents model, prompt, system, and max_tokens. The description adds minimal parameter meaning beyond naming model families and the text response, so it stays at the baseline rather than adding substantial value.
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 uses a specific verb ('Ask'), identifies the resource ('any model from the Store API catalog'), and states the output ('answer as text'). It also mentions distinct model families and the 'second model' use case, which separates it from siblings like list_models, generate_image, and balance.
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 gives clear context: use this when you want to consult a second model from inside the current chat. It does not explicitly name alternatives or exclusions, but the intended use case is evident and the schema points to list_models for obtaining model slugs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Remaining balance on your Store API key, in rubles. — Остаток средств на ключе в рублях.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden. It does state the returned concept (remaining balance in rubles), which implies a read-only query, but it does not explicitly disclose that it is side-effect-free, how authentication failures are handled, or the exact numeric format of the result.
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 English sentence is extremely concise and front-loaded with the essential information. The Russian translation is redundant for an English-speaking agent but does not materially hurt clarity or structure.
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?
Given the zero-parameter complexity and lack of an output schema, the description is nearly sufficient: it tells the agent what result to expect and in what unit. It does not explain the operational context (e.g., balance relevant to sibling paid tools), but that gap belongs more to usage guidance than completeness.
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 has zero parameters, so the schema already fully specifies the input surface; the rubric sets a baseline of 4 for such tools. The description still adds helpful context by naming the API key and the currency, though no parameter-level detail is needed.
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 clearly indicates the tool reports the remaining balance on the Store API key and specifies currency (rubles). It lacks an explicit imperative verb like 'get' or 'check', but the noun phrase is unambiguous and the purpose is clearly distinct from siblings such as generate_image or list_models.
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 gives no guidance about when to call this tool versus the sibling tools, and does not mention preconditions like having a valid Store API key. An agent could infer it is a preliminary check before paid operations, but nothing in the text states this.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate an image from a text prompt and return a link to it. — Сгенерировать изображение по описанию, возвращает ссылку.
| Name | Required | Description | Default |
|---|---|---|---|
| size | No | Size, e.g. 1024x1024 | |
| model | No | Image model, fal-ai/flux/schnell by default | |
| prompt | Yes | Image description |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says the tool generates an image and returns a link, but does not mention side effects (e.g., external API call, resource consumption), required permissions, rate limits, or failure behavior. This is a significant gap for a side-effecting operation.
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, clearly front-loaded sentence that states the operation and output. The optional Russian translation does not add length or complexity. Every word 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?
For a simple tool with three parameters and one required, the description covers the return value (a link) and the core operation. However, it omits details on optional parameter behavior, default values for size, and error handling. Given no output schema, some additional context would improve completeness without overburdening 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?
Schema description coverage is 100%, with all three parameters documented in the schema. The description adds no extra parameter information, so it meets the baseline of 3 but does not exceed it.
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 clearly states the specific verb (generate), the resource (image), and the outcome (return a link). It is distinct from sibling tools like ask_model, balance, and list_models, which serve different purposes.
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?
No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, exclusions, or scenarios where other tools would be more appropriate. The purpose is self-evident but explicit routing is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List available Store API models with prices in rubles per 1M tokens. Use it before ask_model to pick a model. — Список моделей Store API с ценами в рублях за 1 млн токенов.
| Name | Required | Description | Default |
|---|---|---|---|
| provider | No | Filter by provider: openai, anthropic, google, deepseek, qwen, mistral, xai, zai |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral burden. It discloses the pricing unit and currency, which is useful, but it does not describe output shape, ordering, whether provider filtering changes behavior meaningfully, or any limits. This is acceptable for a simple list tool but not richly transparent.
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 English portion is two short, purposeful sentences with the core action and usage guidance front-loaded. The Russian translation duplicates the English content, which is somewhat redundant, but the overall length is still modest and readable.
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 low-complexity tool with one optional parameter and no output schema, the description covers the main decision points: what is listed, in what unit, and when to use it. It could mention what the returned list contains or how the provider filter behaves, but nothing critical is missing for basic invocation.
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% and the single optional provider parameter is already described in the schema. The description adds no new parameter-level semantics, so the baseline of 3 applies.
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 ('list') on a specific resource ('available Store API models') and adds the defining detail: prices in rubles per 1M tokens. This clearly distinguishes it from siblings like ask_model, balance, and generate_image.
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 explicitly instructs to use the tool before ask_model to pick a model, giving clear contextual usage. It does not mention when not to use it or compare against other siblings, but for a simple listing tool the guidance is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
ask_modelbalancegenerate_imagelist_models247 LLMs + image/video/voice/music gen + crypto/DeFi/markets/web-search. Pay-per-call USDC, no key.
Image, video, audio and chat from 61 AI models through one connector. Pay per use, no subscription.
Image, video, music and text generation across 100+ models through one endpoint.
One API key for 6 AI models. Pay-per-use. MCP protocol support with web search.
Add one secure layer between your agents and this server.
