Augenix

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

With only readOnlyHint=false in annotations, the description carries the behavioral burden and delivers: it returns a URL, tells the agent to send that URL, forbids collecting card numbers, and reveals the price is in the result. The 'Do not collect card numbers' instruction is especially valuable compliance guidance for an AI agent.

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?

Each of the six short sentences earns its place: trigger, return value, action instruction, compliance warning, prerequisite, and result content. The usage trigger is front-loaded and there is zero 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?

An output schema exists, so return-value structure is covered structurally. The description covers when to call, the prerequisite, what to do with the result, and a critical compliance boundary. Minor gaps such as failure behavior when the preview isn't ready are acceptable for a one-parameter 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 coverage is 100%, with the token parameter already well documented ('Token returned by start_build. Pass the same token...'). The description adds the state precondition that the preview must be ready, which refines the token's expected state, but doesn't explain the parameter itself. Baseline 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 action—creating a Stripe Checkout link—plus its trigger ('when the owner wants the preview site live') and return value ('Returns a Stripe Checkout URL'). The verb and resource are unambiguous and clearly distinct from the sibling tools' purposes, though it doesn't name them explicitly.

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 opening sentence gives an explicit trigger condition ('Use this when the owner wants the preview site live'), and 'Preview must be ready' states a prerequisite. It provides clear context but stops short of naming alternatives or stating when not to use it (e.g., the follow-up step of using get_live_site after payment).

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 mark the tool as read-only and non-destructive, and the description adds meaningful context about the payment prerequisite and the live=false fallback with the preview URL. This goes beyond the structured fields and clarifies expected behavior in an important edge case.

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 short, front-loaded with the key usage condition, and avoids redundant explanation. It conveys the essential payment-gating behavior in just two sentences without waste.

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 a single well-documented parameter, read-only annotations, an output schema, and a clear payment-dependent behavior, the description is nearly complete. A slight gap is that it doesn't explicitly state what is returned when the owner has paid, although this is strongly implied by the title and tool purpose.

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 already fully documents the token parameter, including its source, reuse across sibling tools, length constraints, and required status. The description adds no additional parameter detail, so the baseline of 3 applies given 100% schema description coverage.

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 indicates the tool retrieves a live site URL and is tied to payment status, with a specific conditional behavior. It distinguishes itself from get_preview by mentioning the preview URL fallback, though it doesn't explicitly name the sibling alternative.

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 timing guidance: use after the owner pays. It also explains the behavior when payment has not occurred, which helps an agent decide whether this tool is appropriate or whether preview-related functionality is needed.

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?

Beyond the readOnlyHint annotation, the description discloses the polling behavior, the meaning of keep_polling and preview_url, the self-refreshing progress card, and the special wait=false mode. These are behavioral facts not available from annotations alone.

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 compact, front-loads the trigger condition, and every sentence contributes a rule or constraint. There is no filler; even the progress-card sentence earns its place by explaining asynchronous UI behavior.

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 polling tool with an output schema and read-only annotations, the description defines the full state-handling loop: when to poll again, when to send the preview URL, when to use wait=false, and when not to restart the build. Remaining details like exact status values are reasonably delegated to 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 schema already documents token and wait with 100% coverage, so the baseline is 3. The description adds value by restricting wait=false to 'progress-card refresh' and emphasizing reuse of the same token, which are usage constraints not fully explicit in the schema.

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 clearly identify a specific action: retrieving and acting on preview build status after start_build. The polling conditions and the explicit 'Do not start_build again' distinguish this tool from start_build and from the other sibling tools.

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 states the exact context ('Use this after start_build'), gives a concrete decision rule for when to poll again, and limits wait=false to progress-card refresh. It also explicitly tells the agent not to call start_build again, preventing a common mistake.

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 indicate non-read-only, non-destructive, so the description carries the behavioral burden. It discloses the async workflow with get_preview, the idempotency warning, and the requirement to use real user-supplied information. It does not describe the exact response, but an output schema exists.

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 dense but every sentence earns its place. It is front-loaded with the core trigger condition, followed by constraints, workflow, and safety warnings. Nothing is vague or redundant to the point of waste.

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 8 parameters and a follow-up polling requirement, the description is remarkably complete: it covers prerequisites, value sourcing, missing-information handling, placeholder prohibition, changeability, polling, and duplicate-call prevention. The output schema handles return-value expectations.

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. The description adds meaningful semantics beyond the schema by emphasizing that name, email, and phone must come from this chat, never from memory, and must not be invented. This is crucial for parameter correctness.

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 purpose: starting a live preview website build for a local service business. It also gives the exact trigger condition ('wants a live preview website' + details typed in chat), which distinguishes it from siblings like get_preview and get_live_site.

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 when-to-use guidance: only when business_name, email, and phone were typed in this chat. It also gives when-not-to-use guidance: don't reuse old details, ask first if only 'build me a website', don't start twice, and call get_preview until preview_url is set.

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