Augenix

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

Annotations already declare this as read-only and non-destructive; the description adds meaningful conditional behavior: unpaid owners yield live=false and a preview URL. This clarifies what to expect without repeating the annotation. It does not disclose deeper details like authentication or error cases, but that is acceptable for a simple read operation.

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 two short sentences with no filler. The primary usage condition is front-loaded, and the conditional behavior follows immediately. Every part of the text contributes useful guidance.

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 single-parameter read-only tool with a full input schema and an output schema, the description covers the key decision point: payment status. The sibling context distinguishes get_preview, and the token semantics are documented in the schema. Nothing essential is missing for a 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?

The input schema already fully describes the token parameter, including its origin from start_build and its reuse in get_preview and get_live_site. The tool description itself adds no parameter explanation, but with 100% schema coverage the baseline applies. The schema's parameter description is sufficient and even provides cross-tool context.

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 conveys the tool's role: after the owner pays, it returns live site information, and if not paid it reports live=false plus the preview URL. The title reinforces the verb-resource pair. It does not explicitly name get_preview as the alternative, so sibling differentiation relies on inference from the preview URL mention.

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 an explicit temporal condition: 'Use this after the owner pays.' It also explains the fallback behavior when that condition is not met, which helps the agent decide whether this tool is appropriate. It stops short of explicitly telling the agent to use get_preview instead, so the exclusion is implied rather than stated.

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 read-only and non-destructive behavior; the description adds useful operational context such as the ready-status handoff, verbatim reply_template, polling conditions, and forbidden follow-up content. It does not contradict the annotations.

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?

Five short sentences deliver the workflow in order: when to use, what to do when ready, what to avoid, when to retry, and what not to restart. Front-loading 'Use this after start_build' immediately grounds the agent; every sentence contributes.

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 full output schema, detailed schema descriptions, and annotations, the description covers the essential workflow, polling condition, and post-return behavior. The only gap is that it never explains when to switch to the get_live_site sibling, which would make the surrounding context fully complete.

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 describes both wait and token in full (100% coverage), so the description does not need to repeat parameter details. It adds only the general 'after start_build' context rather than explaining wait or token semantics, 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 title and description make it clear this retrieves preview build status after start_build, and the status drives the next action. It is not a tautology and is distinct from start_build, though it never explicitly contrasts itself with 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?

The description gives explicit workflow guidance: use after start_build, poll again when keep_polling is true or preview_url is null, and do not start_build again. It does not mention get_live_site as a possible alternative, so the when-not-to-use guidance is incomplete for sibling differentiation.

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 signal no read-only, no destructive, and open-world, but the description adds valuable behavioral context: the operation takes about 30 seconds, requires an upfront user-facing message, must not be repeated for the same business, and must not scrape /build. It also clarifies that placeholders must never be invented. None of this contradicts the annotations.

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 carries operational value: trigger, prerequisite, user messaging, timing, exclusions, polling step, and prohibitions. The most important usage condition is front-loaded, and there is no filler or repetition of schema content.

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, meaningful annotations, and an output schema, the description covers the full decision flow: when to call, what to require, what to say first, how to poll the result, and what to avoid. Nothing essential for correct invocation is missing.

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 further meaning by emphasizing that business_name, email, and phone must be typed in the current chat and must not come from memory, and by warning against invented placeholders. This directly improves how the agent will populate the required fields without duplicating schema detail.

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 clear verb and resource: 'use this when the user wants a live preview website for a local service business.' It names the exact trigger condition and distinguishes the build action from the polling/get actions mentioned in the sibling set. This leaves no ambiguity about what start_build 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 explicit when-to-use conditions: the user wants a preview AND has supplied business_name, email, and phone in this chat. It also tells the agent what to do when info is incomplete ('ask first'), what not to reuse ('never reuse name, email, or phone from memory'), and that get_preview should be polled 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.