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

With no annotations provided, the description carries full responsibility for behavioral disclosure, and it does so thoroughly. It discloses the payment method (USDC on Base via x402/EIP-3009), refusal behavior based on MAX_USD_PER_CALL, asynchronous job_id return, approximate polling time, and prompt screening with no charge on rejection. This is far beyond a minimal 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?

Four sentences, each earning its place: generation, payment/refusal, async polling, and prompt screening. The most important call-defining facts are front-loaded, and there is no redundancy or 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 paid asynchronous tool with no output schema and no annotations, the description provides all critical operational context: cost mechanism, budget refusal, job_id return, polling route, and no-charge rejection. An agent can invoke the tool and handle the follow-up workflow 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?

Schema description coverage is 100%, so the baseline is 3. The description does not add parameter-level detail, but it doesn't need to; the schema already documents every parameter including custom pricing and the audio surcharge. The overall budget context in the description is valuable but not parameter-specific.

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 the exact action, 'Generate an AI video', and immediately distinguishes the tool from siblings like quote_price, get_job, and list_skus by focusing on the paid generation workflow. The title's 'paid' signal is reinforced with concrete billing detail, leaving no ambiguity about what this tool does.

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 workflow context: it quotes a price first, refuses above a budget cap, returns a job_id, and directs the agent to poll get_job until 'succeeded'. It explicitly names the relevant sibling for follow-up, though it does not explicitly route the agent to quote_price for pre-flight price checks or mention when NOT to use this tool.

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 burden of behavioral disclosure. It transparently notes that the call is free, lists the statuses an agent can expect, and warns that the video_url is only downloadable within 24 hours. It does not explicitly state that polling is non-destructive or describe failure response bodies, but the core behaviors are disclosed.

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 short, information-dense sentences that front-load the main action and then list statuses and return behavior. Every word earns its place—'free call', the status enum, and the 24-hour expiry are all valuable without any fluff.

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?

This is a simple one-parameter tool with no output schema, so the description must explain the return value and usage. It does so by stating that success returns a video_url and that the URL expires in 24 hours. The status list helps an agent know what to poll for, and the tool is fully specified 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% for the only parameter (job_id), with the schema already stating that it is the job id returned by generate_video. The tool description does not add any extra semantic detail beyond what is in the schema, 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 uses the specific verb 'poll' with the resource 'generation job', clearly distinguishing it from siblings like generate_video, list_skus, or get_stats. It also enumerates the possible statuses and states that success returns a video_url, which precisely defines the tool's purpose.

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 phrase 'Poll a generation job' clearly tells an agent when to use this tool: after a generation job has been created, to check its status. It gives context for use but does not explicitly mention alternatives or when not to use it, so it falls short of a full 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?

No annotations exist, so the description carries the behavioral burden. It adds useful traits by saying the stats are 'live', 'public', and a 'free call', implying no auth or cost and read-only behavior. However, it does not explicitly state that no mutations or side effects occur, or describe response behavior.

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, tight sentence that front-loads the core purpose and immediately lists concrete metrics. There is no wasted wording or repetition of the tool name.

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, parameterless stats endpoint, the description provides the essential information: it is public, free, live, and what metrics are returned. It lacks output formatting details, but that is a minor gap given the simplicity and absence of an 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 has zero parameters, so there is nothing to document. The description sensibly focuses on the returned metrics instead of parameters, which is appropriate for a parameterless endpoint.

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 returns live gateway reliability stats and lists the specific metrics (success rate, p50 generation seconds, total delivered). It is clear about the resource and function, though it does not explicitly differentiate itself from siblings; the distinct metrics make differentiation easy.

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 about when to use this tool versus alternatives. 'Live public stats' implies a use case, but there is no explicit context, exclusions, or mention of when other sibling tools would be more 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?

With no annotations, the description carries the behavioral burden and does well: it discloses that the data is live, prices are in USD, the call is free, and covers both fixed and custom endpoint variants. It stops short of explicitly confirming read-only/no side effects, but 'live catalog' strongly implies a non-mutating lookup.

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 sentences front-load the core purpose ('live catalog... with current USD prices') and then pack precise pricing detail and endpoint categories without filler. Every clause 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 zero-parameter listing tool with no output schema, the description is complete: it tells the agent what the call returns, how current it is, that it is free, and what pricing/customization variants exist. No additional information is needed to invoke it 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 input schema has zero parameters, so the 0-param baseline of 4 applies. The description adds useful semantic context about what the no-argument call returns (pricing catalog) even though there are no parameters to document.

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 title and description together define a specific resource: a live catalog of pay-per-call video generation endpoints with current USD prices. It clearly distinguishes this listing tool from siblings like quote_price and generate_video, which handle pricing quotes and generation rather than catalog enumeration.

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 implies this is the tool to call for checking current catalog prices (it explicitly notes the call is free), but it does not state when to prefer it over alternatives like quote_price. The fixed-price vs. custom-endpoint distinction hints at routing, but no explicit when/when-not 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?

With no annotations, the description carries the safety burden, and it explicitly discloses that the call is free and does not require payment. This is the key behavioral trait for a quoting tool. It does not mention rate limits, quote validity, or whether the quote is binding, but the main side-effect risk (accidental payment) is clearly addressed.

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 sentence with zero filler. It front-loads the core purpose, then adds the two most useful qualifiers: 'without paying' and 'useful before generate_video.' 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?

Given the moderate complexity of 8 parameters and no output schema, the description covers purpose, usage timing, and the return semantic (exact USDC price). The schema covers all parameter details. It could mention response format or quote validity, but the tool's intent is fully understandable from this description alone.

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 input schema already documents all eight parameters, their defaults, enums, and constraints. The tool description adds no parameter-level semantics beyond the generic 'generation request' framing. Baseline 3 is appropriate because the schema does the heavy lifting.

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: 'Get the exact USDC price for a generation request.' It clearly distinguishes itself from the sibling generate_video by emphasizing 'without paying,' and the title 'no payment' reinforces this. An agent can immediately tell this is a quoting tool, not a generation or stats tool.

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?

Gives clear procedural context: 'useful before generate_video.' This tells an agent when to call it. It does not explicitly spell out when not to use it or name alternative tools, so it stops short of a 5, but the workflow guidance is unambiguous.

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 bears full responsibility. It discloses that the call is free (no payment/wallet), is read by a human (implying asynchronous, non-immediate handling), and that it serves as a channel for escalation. It doesn't mention response behavior or rate limits, but these are minor for a feedback 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?

Two sentences with high information density. The key facts (free, human reads) are front-loaded, and the list of use cases is compact yet comprehensive. No filler words; every clause adds value.

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 feedback submission tool with 6 parameters and no output schema, the description covers cost, purpose, triggers, and preferred alternatives. It doesn't explicitly state that the call is asynchronous or that no immediate response is expected, but this is implied by the human-read note. Overall, adequate for an agent to invoke 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 schema covers 100% of parameters with descriptions, so the tool description adds little per-parameter detail. However, it provides examples of missing features (wait_for_job, reference images) that implicitly guide message construction and category selection, slightly exceeding the baseline of 3.

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 it sends product feedback to humans, with specific triggers like incorrect pricing, poor output quality, missing features, cheaper sources, and bugs. It distinguishes itself from sibling tools (list_skus, get_stats, etc.) by being an action for reporting issues rather than data retrieval or 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?

Explicitly lists when to use the tool ('Use when...') with concrete examples, and instructs to prefer it over silently retrying or dropping the task. This gives clear decision criteria and alternatives, leaving little to inference.

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