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

With only openWorldHint in annotations, the description adds meaningful behavior: it is asynchronous, returns a task ID, and is billed to the Modelflare balance by actual usage. It does not cover auth requirements, rate limits, error handling, or idempotency for a task-creation tool.

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 tight sentences: purpose first, then the polling/download workflow, then billing. Each sentence earns its place and there is no redundant restatement of the tool name or schema.

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 description covers what the tool returns (task ID), how to proceed afterward (get_video_status, download_video), and the billing model. With full schema coverage for the nested request object and no output schema, this is complete enough for correct invocation and follow-up.

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 schema already explains both model and request in detail, including references to list_models and the model's docs page. The description itself adds no parameter-level meaning, so the baseline 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 states a specific verb and resource: it 'Starts an asynchronous Modelflare video task and returns its task ID.' It also names get_video_status and download_video as follow-up tools, clearly distinguishing this as the task-creation step rather than polling or saving.

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 explicit next steps: poll with get_video_status and save with download_video. However, it does not state when this tool should be chosen over siblings like generate_image or list_models, nor does it mention preconditions or exclusions.

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 only declare openWorldHint, leaving the description to carry most of the behavioral burden. It does disclose the side effect (writes a file to the output directory) and the expiry constraint on result URLs, but says nothing about auth requirements, overwrite behavior if the file already exists, or error/timeout handling.

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 short sentences, front-loaded with the core action and destination, then optional behavior, then the urgency constraint. No filler or repetition.

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 openWorldHint in annotations, the description covers the essentials (destination, optional wait, expiry) but omits the file naming/return value and any failure modes. Adequate, but an agent still has to guess at specifics after the call.

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 50%: wait_seconds is fully documented in the schema, while task_id is undocumented there. The description's 'waits for the task first' merely restates wait_seconds and never clarifies what task_id is or where to obtain it, so it does not compensate for the coverage 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 verb ('Saves') and resource ('a completed Modelflare video') plus the destination ('the output directory'), so an agent can distinguish it from create_video and get_video_status. It stops short of naming or explicitly contrasting any sibling, which keeps it from the top band.

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?

'Optionally waits for the task first' and 'download soon after completion' give clear context on when to call this (post-completion, promptly, with an optional wait). There is no explicit exclusion or named alternative such as checking get_video_status first, so it falls short of a 5.

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 only openWorldHint provided, the description carries the behavioral burden and adds real value: it discloses that the result is written to an output directory and that the call is billed to the Modelflare balance by actual usage. It does not cover authentication/permission needs or failure behavior, but the cost and side-effect disclosure is substantive.

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 compact clauses, front-loaded with the core action before the billing note, with no filler. The edit-mode distinction is placed early where it is most actionable.

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 4-parameter tool with a nested passthrough object and no output schema, the description usefully states where output lands and how billing works, covering the main gap left by the missing return schema. It does not warn about model-specific field requirements in the nested parameters object, but the schema covers that.

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; the description only reinforces edit=true and the list_models source for model. It adds no meaning for prompt or the nested parameters passthrough object, so it does not compensate beyond the schema baseline.

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 names a specific verb+resource (generates/edits an image) and splits the two modes via the edit=true flag, which is precise enough to act on. It does not explicitly contrast with siblings like create_video, but the resource is distinct enough that confusion is unlikely.

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 states that edit=true switches to the edit route and that the model ID comes from list_models, implying a prerequisite lookup. However there is no explicit when-to-use/when-not guidance, no mention of the create_video sibling, and no conditions under which generation versus editing should be preferred beyond the boolean flag.

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=true and openWorldHint=true, so safety is covered. The description adds only that a "status and progress" value is returned, with no polling semantics, terminal states, expiry/failure behavior, or rate limits, which is thin for a task-status tool.

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 no filler. It is efficiently sized, though arguably under-specified rather than deliberately terse.

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 one-parameter read-only poll tool with annotations covering safety, this is close to adequate, but with no output schema the agent gets no sense of what "status and progress" actually contains (state enum, percentage, error field), and the task_id origin is unexplained.

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% for the single task_id parameter, so the schema provides no meaning. The description never explains what a task_id is or where it comes from (presumably create_video), leaving the only parameter undocumented in both places.

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 ("Returns") and resource ("status and progress of a Modelflare video task"), which is distinct from create_video, download_video, generate_image, and list_models. It does not explicitly name or contrast with any sibling, so an agent must infer the polling role.

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 when-to-use guidance, no mention of polling after create_video, and no note on how often or when to call it. Usage is only implied by the word "status".

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 and openWorldHint, so the safety profile is covered. The description adds genuinely new behavioral context: results are scoped to what the API key is authorized to call, the filter defaults to image+video rather than returning everything, and the response carries a docs page with each model's exact request contract.

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-loaded with the core action and scoped by the API key before mentioning the filter default. The phrase 'with the docs page that holds each media model's exact request contract' is slightly long but carries useful information about the return value, so it 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 one-optional-parameter, read-only discovery tool with no output schema, the description covers scope, authorization bounds, default filtering behavior, and the key content of the response (docs/request contract). An agent can call it correctly, though it could go one step further and position it as the prerequisite step for the generation siblings.

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% and the enum values are self-documenting, so the baseline would be 3. The description nonetheless adds semantics the schema lacks: what the result set looks like when kind is omitted (image and video only), which resolves the default-value question for the single optional parameter.

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: lists the Modelflare models the current API key can call, and adds that the payload includes each media model's docs URL. That scope is clearly distinct from the generation/status siblings (create_video, generate_image), though the description never names those siblings explicitly to route the agent.

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 only usage signal is the implicit default ('Defaults to image and video models'), which tells the agent what happens when the kind filter is omitted. There is no explicit guidance such as 'call this first to discover valid model identifiers before generate_image/create_video', and no statement of when NOT to use it.

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