370.ai — AI Gateway: 100+ Chat Models, Image & Speech Generation

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

No annotations are provided, so the description bears the full burden. It tells the agent that the tool returns the model's text reply, describes the 'model' default as 'fast cheap default', and explains parameter effects. However, it does not disclose potential costs, rate limits, or any side effects beyond the reply. There is no contradiction with annotations (none exist), but transparency is only partial.

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 front-loaded with the core purpose, followed by concise guidance and a neatly tabulated Args list. No filler or redundant sentences; every line earns its place. The structure is highly readable and aids an agent's quick parsing.

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 chat tool with 5 parameters, the description covers purpose, usage scenarios, parameter semantics, and the return value ('Returns the model's text reply'). It also references list_models for the full model catalog, and the existence of an output schema reduces the need to detail return format. Missing error-case or rate-limit info, but the essentials are sufficiently covered.

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 has no parameter descriptions (0% coverage), so the description compensates well. It explains each argument: prompt is 'the user message / question', model is a 'model id' with empty meaning 'fast cheap default', system is 'optional system instruction', max_tokens is 'optional cap on output length', and temperature is '0..2'. This adds meaning beyond the bare schema types and defaults.

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 tool's function: 'Ask any text/chat model on 370.ai ... and get its reply.' It explicitly names the resource (models on 370.ai) and the action (ask/get reply), and distinguishes it from sibling tools like generate_image or text_to_speech.

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?

Provides explicit use cases: 'when you want a specific or different model than your own', gives concrete examples (consult Claude while on GPT, cheaper model for bulk work), and points to list_models for the catalog. Lacks an explicit 'when not to use' but the alternative is implied through list_models.

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?

No annotations are provided, so the description must carry the burden. It discloses that the tool 'Returns the generated PNG image,' which is a behavioral trait. However, it does not mention other behaviors such as whether the operation is synchronous, any API key requirements, rate limits, or potential side effects. For a simple image generation tool, the return type and size options provide some transparency, but not a full picture.

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 concise and well-structured: a single-purpose first sentence, followed by a compact args list. Every sentence earns its place with no extraneous detail. The format is easy to scan and understand.

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 low complexity (2 params, 1 required) and absence of an output schema, the description covers the essentials: purpose, parameter semantics, and return format. It does not address edge cases or failures, but for a simple generation tool this is reasonable and not a critical 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?

The schema description coverage is 0%, so the description fully compensates. It explains 'prompt' as 'description of the image' and adds the tip that 'English works best.' For 'size,' it enumerates the exact allowed values and their orientation meanings (square, portrait, landscape), which is not present in the schema. This significantly helps the agent select appropriate parameter values.

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 tool's verb ('Generate') and resource ('an image from a text prompt'), which distinguishes it from sibling tools like generate_video and text_to_speech. The phrase 'picture/illustration/photo' further clarifies the 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?

The description explicitly states when to use the tool: 'Use whenever the user wants a picture/illustration/photo created.' This is clear positive guidance. It does not explicitly mention exclusions or alternatives, but the context of sibling tools implies that for non-image generation, other tools are appropriate.

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?

No annotations are provided, so the description carries the burden. It discloses two genuine behavioral traits: the result is scoped to the API key's permissions ('your API key can call'), and the call is free with no billing impact. It doesn't mention ordering/pagination, but for a no-parameter discovery call that is a minor omission.

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 the verb and resource first, then the scope and a parenthetical enumeration of modalities, then the cost note. Every clause earns its place and nothing is 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?

An output schema exists, so the description need not document return values. For a zero-parameter read tool it covers scope, cost, and content adequately; the only gap is explicit guidance on when to prefer it over the generation siblings, which is minor.

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. The description correctly implies no input is required beyond the API key, matching the empty schema; there are no parameters whose semantics need explaining.

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 ('List') and resource ('every model id your API key can call') and enumerates the modalities (chat/image/video/audio). This distinguishes it cleanly from the generation siblings (chat, generate_image, text_to_speech), which act on models rather than enumerate them.

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 is implied: an agent would call this to discover which models are available before invoking a generation sibling. However, there is no explicit when-to-use or when-not guidance, nor a stated alternative for model discovery. 'Free, no billing' hints that cost is not a blocker but does not route the agent.

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?

With no annotations, the description carries the full burden and does well: it discloses the cost model ('billed per input character'), the non-obvious default-model voice aliasing gotcha, and the return shape (status line plus audio content block with gateway mimeType). It does not mention auth requirements or rate limits, but the key behavioral surprises are covered.

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 purpose sentence, then structured Args/Returns sections. The voice paragraph is the longest block but every clause is actionable (accepted names, aliasing behavior, workaround), so it earns its space.

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 supplies the return format itself, plus cost and parameter guidance. For a two-parameter tool this is close to complete; only error/failure behavior and auth expectations are absent.

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%, so the description must compensate, and it does: it defines 'text' and gives substantial meaning for 'voice' beyond the schema — which named values are accepted, why they collapse to one voice on the default model, and concrete alternatives (Cherry/Ethan). This is real added value the schema lacks.

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?

Opens with a specific verb+resource ('Convert text to spoken audio') that is immediately distinguishable from siblings chat, generate_image, and list_models. No ambiguity about what the tool produces.

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?

Provides practical context — billing is per input character, and the voice paragraph tells the caller how to actually get a distinct voice. However, it never states when to use this tool versus the siblings (e.g. for audio output vs text), so the when-to-use dimension is only implied.

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