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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description still adds useful behavior beyond them by disclosing that the values are estimates and that results cover three distinct time windows plus budget remaining. It stops short of saying how fresh the estimate is or where budget data originates.

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?

One sentence, zero filler, with the most important information (what is returned) front-loaded. Nothing could be removed without losing meaning.

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 zero parameters, read-only annotations, and an output schema that documents the return shape, the description covers nearly everything an agent needs to select and call it. The only remaining gap is data freshness/estimation basis, which is minor given the output schema.

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 no parameters and the schema is an empty object, so there is nothing for the description to disambiguate. Baseline 4 applies since no semantic gap exists.

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 pairs a specific verb ("Show") with a specific resource ("estimated spend" / "remaining budgets") and enumerates the aggregation windows (today, this month, total). It leaves no ambiguity about what the tool returns; only an explicit nod to the sibling image/video tools is absent, and those are unrelated enough that no differentiation is needed.

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 only implied: an agent can infer this is the tool to call for spend/budget questions, but there is no explicit when-to-use framing, no statement of prerequisites (e.g. authentication or billing scope), and no named alternatives. For a zero-parameter reporting tool that is largely self-evident, this is adequate but not instructive.

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 write (readOnlyHint=false), non-destructive, and open-world behavior, so the description should add operational context such as whether results are written to disk, expected latency, or cost implications. It adds none of that; 'according to the prompt' restates the obvious. The only unstated-but-inferable behavior, file output, comes from the schema's output_name, not the description.

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 or redundancy. It is efficient, though its brevity is part of why behavior and usage remain under-explained.

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 has an output schema and full parameter documentation, so the description need not explain return values. However, for a six-parameter, open-world generation tool that writes artifacts, it omits file-output behavior, cost considerations (a cost_report sibling exists), and model selection implications, leaving meaningful gaps for an agent deciding between edit_image and generate_image.

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 model, prompt, resolution, image_paths, output_name, and aspect_ratio are all documented in the schema itself, which sets the baseline at 3. The description contributes no additional parameter meaning beyond what is already structured.

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 pair (edit/combine) and resource (images) plus the driving input (the prompt), so an agent knows it transforms supplied images rather than creating new ones. It stops short of naming generate_image as the alternative, so differentiation is implied by 'one or more images' rather than stated.

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 only implied: the phrase 'edit or combine one or more images' signals that reference images must exist, which separates it from generate_image. There is no explicit when-to-use, when-not-to-use, or cost/quality tradeoff guidance relative to the sibling generation and model-listing tools.

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=false, openWorldHint=true and destructiveHint=false, so the mutating, open-world nature is known. The description adds genuinely new behavioral context that annotations cannot express: the call incurs monetary cost and is budget-checked before execution. It does not say what happens when the budget check fails or whether generation is synchronous.

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 sentences with no waste, and the cost caveat is placed early enough that an agent sees it before committing to the call. Every clause carries 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?

With an output schema present, return values need no explanation, and all five parameters are fully described in the schema. The cost-and-budget note covers the main non-obvious risk; only edge behavior (budget rejection, failure modes) is left unstated, which is a minor gap for this complexity.

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 every parameter including model, resolution, aspect_ratio and output_name is already documented in the schema. The description adds no syntax, defaults, or constraint detail beyond that, which is the expected baseline when the schema does the work.

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 and resource ("Create an image") plus the input modality ("from a text prompt"), which implicitly separates it from edit_image and start_video. It stops short of naming a sibling explicitly, so an agent must infer the boundary rather than being told.

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 explicit when-to-use or when-not-to-use guidance and no mention of alternatives such as edit_image for modifying an existing image. The only steer is the implied contrast in "from a text prompt", and nothing tells the agent to call list_models first for a model ID, even though a sibling exists for that.

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?

The annotations declare readOnlyHint=false without saying why; the description resolves that by disclosing that a completed job writes an MP4 into the output directory. That is genuinely additive context. It stops short of covering repeated-call behavior (does a second call re-download?), where the output directory is, or what happens on failure.

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?

One short sentence that front-loads the action and appends the conditional side effect. Nothing is redundant and nothing needs to be skimmed past.

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 return values need no explanation, and the write side effect is covered. However, for a polling tool that produces files, the description omits whether the call blocks until completion, whether it is safe to repeat, and where the downloaded artifact lands relative to other tools.

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?

There is a single parameter with 100% schema description coverage, and the schema already explains that job_id comes from start_video. The description adds no format, validation, or provenance detail beyond that, 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 verb and resource (check a video job) and adds the terminal side effect (download the MP4). It is clearly distinct from sibling start_video and from the image tools, though it never names start_video explicitly as the originating call.

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 only implied: 'check a video job' suggests calling it after job submission, and the schema's 'job_id returned by start_video' fills that gap. There is no explicit when-to-use, no guidance on how often to poll, and no statement about what to do if the job failed or is still running.

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 establish readOnlyHint=true and openWorldHint=false, so much of the safety profile is covered. The description adds one genuinely new behavioral fact — that it returns only configured models plus price estimates and supported options — but says nothing about auth, rate limits, or pagination.

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; every clause (configured models, estimated prices, supported options) carries information about the response.

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 input parameters, an output schema in place, and annotations covering the read-only profile, the definition supplies nearly everything an agent needs. The only gap is the missing cue about where this call fits relative to cost_report and the generation tools.

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 there is nothing for the description to disambiguate beyond what the empty schema already conveys. Baseline 4 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 opens with a specific verb+resource ("List configured models") and states the payload (estimated prices and supported options). It is clearly distinct from the sibling tools, which all generate or edit media or produce a cost report, but it does not name those siblings explicitly to reinforce the boundary.

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 only implied: mentioning estimated prices and supported options hints that this is a discovery call to make before generate_image, start_video, or cost_report, but the description never says when to call it or when not to. No prerequisites or ordering guidance is given.

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 establish that this is a non-read-only, open-world, non-destructive operation, so the description only needs to add context. It usefully discloses the asynchronous contract (returns immediately, no waiting), but omits the paid/cost-gated nature of the call and the fact that confirm_cost=false merely quotes a price, which is the most consequential behavior here.

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 async guarantee parenthesized for emphasis. Every clause earns its place and nothing is padded.

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 return values need no explanation, and the async nature is covered. However, for a job-starting tool sitting next to get_video_status, the description should say what to do after receiving job_id and note the cost-confirmation requirement, both of which are left unstated.

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 explains all seven parameters including confirm_cost's gating semantics. The description adds no parameter-level meaning beyond that, which is the expected baseline when the schema does the work.

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 ('Start a video generation job') plus the immediate return ('job_id'), which cleanly separates it from the polling sibling get_video_status. It stops short of naming that sibling, so the differentiation is inferred rather than explicit.

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 waiting' implies this is the kickoff call and that status is checked elsewhere, but the description never names get_video_status as the follow-up. It also gives no guidance on when to use this versus generate_image or when the cost-confirmation step applies.

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