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 the return value (assistant reply text) but does not mention side effects, rate limits, auth, or error behavior. For a simple chat tool this is acceptable but not rich.

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 sentences with zero waste. The purpose and return type are front-loaded, and the example provider list adds value without bloat.

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 chat tool with 4 well-described params and no output schema, the description covers the return type and scope. Nothing critical is missing for an agent to call it correctly, though it could mention streaming or multi-turn if relevant.

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% – all four parameters have descriptions. The description adds no additional meaning beyond the schema, so baseline 3 applies. The examples in the schema are sufficient.

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 (chat/text completion) and resource (any LLM on apimodels.app) and explicitly lists example providers. Clearly distinguishes from siblings like generate_image and text_to_speech by focusing on text generation.

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?

Implies usage for text-based chat and completion, and the sibling tool names (generate_image, generate_video, text_to_speech) make the boundary obvious. However, it does not explicitly state when not to use it or name alternatives for text tasks.

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 provided, the description carries the full burden of behavioral disclosure. It discloses that URLs expire after 7 days, that a downscaled preview may be attached, that generation is not free (with approximate costs), and that review_image should be used as a fallback when the image cannot be seen. This is substantial, useful behavioral context.

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 three sentences with no filler: purpose first, then output behavior, then fallback workflow and cost. Every sentence contributes actionable 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?

The tool is reasonably complex with 6 parameters and no output schema, and the description still explains return values, URL lifetime, preview behavior, costs, and the follow-up workflow. It is slightly shy of full completeness because it does not describe failure modes or edge cases, but it is sufficient for correct invocation in most cases.

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 baseline is 3, but the description adds value by explaining cost tradeoffs between models and the practical meaning of returning vs. previewing images. This goes beyond the raw schema descriptions for model and return_image.

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 ('Generate an image from a text prompt') and immediately covers the alternate mode ('or edit an input image'), clearly distinguishing the tool from siblings like generate_video and review_image. The verb and resource are 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 description gives explicit guidance for the review_image alternative: if the agent cannot see the result, call review_image with the URL and use its revised prompt. It also provides model-cost guidance for choosing gpt-image-2-lite, though it does not explicitly discuss when to prefer generate_video or chat.

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 to lean on, the description discloses several behavioral traits: it polls until done, returns URLs valid for 7 days, may take a few minutes, and carries specific cost implications. It stops short of describing failure modes, rate limits, or authentication requirements, but the core behavior an agent needs to know is 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?

The description is three sentences with every sentence earning its place: the first defines the function, the second covers behavior and duration, and the third adds cost guidance. Key information is front-loaded and 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?

For a tool with no output schema, the description adequately explains return format (video URL(s)) and longevity (7 days). It covers the long-running nature and cost considerations. It could add error/edge-case behavior, but the schema already documents model name failures, so this is a minor 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 coverage is 100%, so the baseline is 3, but the description adds extra value by explaining cost behavior and pointing to a specific model value (veo-3.1-fast-fhd) as the cheapest option. It also reinforces the prompt/image relationship, going slightly beyond what the schema states.

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 primary action ('Generate a video') and the input modality ('from a text prompt (and optional reference image)'), making the resource and scope unmistakable. It differentiates itself from sibling tools like generate_image and text_to_speech by the video resource and by noting it is the most expensive modality.

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 for use: it polls until done, may take minutes, and is the most expensive modality, which helps an agent decide whether video generation is appropriate. It does not explicitly name sibling alternatives or provide when-not-to-use rules, but the context is strong enough to guide a reasonable selection.

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 behavioral burden. It reveals a non-obvious behavior: some IDs returned are internal names that generation endpoints reject, and explains the dotted alias convention. This is meaningful behavioral disclosure beyond a simple 'list' statement.

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?

Three sentences, each serving a clear purpose: stating the resource, connecting it to sibling tools, and providing a vital troubleshooting caveat. No filler or repetition, and the most important usage context is front-loaded.

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 parameterless listing tool with no output schema and no annotations, the description is complete: it defines the resource, the modalities, the intended downstream use, and the known edge case. An agent has everything needed to invoke and interpret the result 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?

The tool has zero parameters, so the schema is trivially complete. The description correctly omits parameter details and instead focuses on output semantics and caveats, which is the appropriate use of description space for a parameterless tool.

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 explicitly that it lists model IDs from apimodels.app across specific modalities (chat, image, video, audio), and frames the purpose as supplying IDs for the sibling tools. This clearly distinguishes it from the generation tools in the sibling list.

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?

Directly instructs the agent when to use the tool: before calling other tools, using returned IDs as inputs. The caveat also gives actionable guidance on handling invalid IDs by trying the dotted variant, which is precisely when-to-use-and-what-to-do 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?

No annotations are provided, so the description carries the full disclosure burden. It adds genuinely useful behavioral context: cost ('one small vision chat call, well under $0.01'), the shape of the return value, and a portability trait (works in every MCP client). It stops short of stating whether the call has side effects or how it behaves on failure, 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?

Three sentences, front-loaded with the core purpose, then usage context, then a cost note. Every sentence carries distinct information and none of it repeats what the input schema already states.

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 3-parameter tool with 100% schema coverage and no output schema, the description covers what it returns, when to call it, and what it costs. The only gaps are error behavior and an explicit statement that the operation has no side effects, which are minor for a review-style read 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 description coverage is 100%, so the baseline is 3. The description adds workflow context by implying image_url is typically 'a URL returned by generate_image' and framing brief as the original generation prompt, but the schema already documents both parameters thoroughly, so the marginal gain is modest.

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 ('Have a vision model look at an image and critique it against a brief') and enumerates the output: what matches, what is wrong (garbled text, composition, colors, artifacts), and a revised prompt. The explicit placement as the follow-up to generate_image distinguishes it from the generation siblings without needing to open 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?

'Use it after generate_image to check the result and decide whether to regenerate' is an explicit trigger condition with a clear decision outcome. The clause 'works in every MCP client, including ones that do not pass tool-result images to you' gives a concrete reason it beats the alternative of relying on native image display.

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 supplied, the description carries the full disclosure burden. It adds meaningful non-obvious behavior: the result is a URL rather than a streamed file, the URL expires after 7 days, and the operation has real monetary cost. It does not cover latency, failure modes, or rate limits, but the disclosed behaviors are valuable.

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 sentences front-load the core action and then deliver the most important behavioral details: output URL, expiry, and cost. Every sentence earns its place with no redundant 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?

For a simple 4-parameter tool with full schema documentation and no output schema, the description covers the return format, URL validity, and cost. The main missing piece is explicit routing guidance versus streaming or other siblings, but the essential invocation context is present.

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 every parameter already has a type, default, and explanatory description. The tool description adds no parameter-specific semantic content beyond the schema, so the baseline score of 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 opens with a specific verb and resource: 'Convert text to speech (MiniMax voices).' It clearly differentiates this audio tool from the sibling media tools (generate_image, generate_video) and chat, and adds concrete return behavior ('Returns the audio file URL').

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 guidance about when to use this tool versus alternatives, and no mention of exclusions such as streaming TTS via a sibling endpoint. The cost information is useful but does not help the agent choose between text_to_speech and related tools.

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