Scowty

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

The annotations already declare readOnlyHint, idempotentHint, and non-destructive status, so the safety burden is covered. The description still adds real behavioral context beyond that: it states the scope is limited to the homepage and warns that the call takes up to a minute.

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, and the purpose and outputs are front-loaded ahead of the latency note and the input note. No sentence is filler, and each one adds distinct 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?

For a one-parameter read-only tool with no output schema, the description is nearly sufficient: it names all three return values and discloses latency. The only gap is the accepted address format, which is left for the caller to guess.

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 only one parameter and the schema description coverage is 0%, so the description has to carry the parameter's meaning. 'Input is the website address' clarifies that it expects a web address rather than a business name, but it never specifies the format: whether it needs a scheme, whether it can include a path, or why the length is capped at 253.

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 gives a specific verb ('Audits') and resource ('an existing website's homepage') and spells out the three return values: health score, AI citation frequency, and top two fixes. It never names the sibling tools however, so an agent must infer that this is different from check_website_preview rather than being told so.

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 implies usage through 'existing website' and 'Input is the website address,' which hints this audits a live site rather than a preview, but it never explicitly states when to use this over check_website_preview or start_website_preview. There are no exclusions or prerequisites 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 readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered structurally. The description adds that the operation is asynchronous ('When the build is done'), which is genuinely useful, but says nothing about in-progress or failed states, polling cadence, or expiration of the job.

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, no filler, with the core behavior front-loaded and the return values following. Slightly tight given it omits status semantics, but every sentence 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?

With no output schema, the description usefully enumerates what comes back on success, which is the key information for a one-parameter polling tool. Missing failure/pending state descriptions and job-expiry semantics keep it from being 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?

Schema description coverage is 0%, so the description must compensate; it implies the jobId originates from start_website_preview but never names the 'jobId' parameter or states that the returned job identifier is what must be passed in. The linkage is inferable but not spelled out.

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 ('Returns the status of a preview') and explicitly ties the resource to its sibling 'start_website_preview', so the agent can distinguish this poller from the starter tool. It also names the concrete payload returned on completion (preview link plus account-save link).

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 'a preview started with start_website_preview' establishes the precondition and the correct ordering relative to that sibling. It stops short of explicit polling guidance (how often to re-check, when to stop) or any when-not-to-use exclusion, so it is clear context rather than a complete usage policy.

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 already declare readOnlyHint, idempotentHint, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description repeats 'Read-only' and adds that a pricing-page link is returned, but it does not add details such as authentication, rate limits, or response shape.

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 and front-loads the key return information. There is no redundant or wasted language beyond the minor repetition of the read-only annotation.

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, read-only lookup tool, the description is nearly complete: it names the returned data and the pricing-page link. Because there is no output schema, it could have specified the response structure a bit more, but the complexity is low enough that this is a minor gap.

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 parameter semantics are inherently simple. With no parameters to document, the baseline is 4 and the description does not need to compensate for missing schema details.

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: it returns Scowty's current products, prices, and a pricing-page link. The purpose is clear and distinct from the sibling preview and AI-visibility tools, though it does not explicitly differentiate itself from them.

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 implied by the resource being returned: an agent should call this when it needs current plans and pricing. The description provides no explicit when-to-use, when-not-to-use, or alternative tool guidance.

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 non-read-only, non-idempotent, non-destructive, closed-world behavior. The description adds genuinely useful async context: it returns a job id immediately and the build takes two to three minutes, with polling guidance. It does not cover auth, cost, or failure behavior, so it is strong but not complete.

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 tightly written sentences front-load the action and then the async return and follow-up timing. 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 an async job-creating tool with no output schema, the description explains the immediate job id return and the expected build duration plus polling path. The main gap is the undocumented state and industry parameters, which leaves the input contract incomplete.

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%, so the description must compensate. It names businessName, businessType, city, and services and clarifies 'up to three main services', but it omits the state and industry parameters entirely, leaving two of six inputs undocumented.

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 ('Starts building a preview website') and scopes it to a small service business with named inputs. It is clearly distinguishable from check_website_preview, which only checks status.

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 explicitly directs the agent to call check_website_preview with the returned job id about a minute later, establishing the correct follow-up workflow. It stops short of stating when not to use this tool or comparing against other siblings like get_plans_and_pricing.

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