SORNKan Worldsite

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

Annotations are empty, so the description carries the full burden. 'Go live' implies a state change but does not disclose consequences, permissions required, or reversibility. The advisory to ask a human hints at importance but does not explain what the tool actually does or what side effects occur.

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 extremely short, which could be concise, but it omits essential information. Under-specification is not conciseness; every sentence should add value, and here the only additional sentence is a safety caution that doesn't explain the tool.

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, no annotations, and a vague description, the tool is completely inadequate for an agent to understand when and how to invoke it. The tool has two parameters, one required, and no indication of expected behavior or results. It lacks critical context even for a simple action.

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 0%, so the description must compensate for the two parameters (slug, uploadId), but it provides none. There is no indication of what these parameters mean, how they relate to the action, or their formats. This fails to add any value beyond the bare 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 description 'Go live' is vague and does not specify the resource or action clearly. It does not distinguish from sibling tools like 'publish_website' or 'claim' (implied by the name but not explained). This is barely more than a tautology of the tool name.

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 context about when to use this tool versus alternatives is provided. The only instruction is 'Ask the human before calling this,' which is a caution but not a usage guideline. There is no mention of prerequisites, scenarios, or when not to use it.

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 description discloses the core connection method (CNAME only), that it is not a registrar operation, and the recurring cost (+$1 USDC/month). Since annotations are empty, this carries some behavioral burden, but it omits side effects, prerequisites, or whether the connection is reversible.

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 concise sentence that front-loads the action, constraint, and price with no filler. Every phrase 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?

The tool is simple, but the description omits what slug refers to and what the user should do after connecting (e.g., CNAME target, verification). The price and CNAME-only constraint help, but the missing parameter meaning leaves invocation ambiguous.

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?

For hostname, the description supplies meaning: the parameter is the existing custom hostname to connect. However, slug remains unexplained, and with 0% schema description coverage, the description only partially compensates for the undocumented parameters.

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 ('Connect') and identifies the resource ('an existing hostname'), along with the method ('via CNAME only') and pricing. This clearly distinguishes it from sibling tools like claim, edit, and publish_website.

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 'via CNAME only (no registrar)' sets a clear use context: this is for hostnames the user already controls and wants to attach via CNAME, not registrar transfers. However, it does not explicitly name alternative tools or say when not to use them.

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 are empty, so the description must carry behavioral disclosure. It reveals the tool is token-metered and that JS uses paid GLM, but does not describe side effects, prerequisites, or what gets changed. Limited transparency beyond cost.

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 concise (two short sentences) and front-loaded, but it is under-specified. Conciseness is preserved, but it lacks substance to be effective.

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 three parameters and no output schema, the description is severely incomplete. It does not explain the tool's function beyond a vague action, nor does it cover parameters or behavior. Inadequate for an agent to use 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 coverage is 0% and the description does not mention slug, uploadId, or tokens. It adds no meaning to the parameters, leaving the agent without any clue about their purpose or format.

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 the action ('Re-scan and redeploy') but does not specify the resource or how it differs from siblings like inspect or publish_website. It is a vague purpose, not a tautology, but lacks specificity.

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 provides no guidance on when to use this tool versus alternatives. It only mentions cost and GLM usage, which are not usage context. No exclusions or conditions are provided.

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 behavioral burden. It discloses a key behavioral trait — 'Ask the human before going live' — indicating a human-in-the-loop guardrail. However, it does not clarify whether scanning mutates anything, what side effects (if any) occur, or what the output of a scan is.

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, front-loaded with the core action. No filler or redundancy; every word 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?

For a simple one-parameter tool with no output schema, the description covers the key context: inspecting an uploaded zip and requiring human approval before going live. It is slightly thin on what 'scan' entails, but the low complexity and sibling context make it adequately 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 schema has no parameter descriptions, so the description must add meaning. 'Uploaded zip' gives useful context that uploadId refers to a previously uploaded zip file. It does not explain how to obtain uploadId or what format to expect, but it provides minimal necessary semantics.

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 'scan' with the resource 'an uploaded zip', clearly distinguishing it from siblings like upload_url, edit, and publish_website. It unambiguously identifies what the tool acts on.

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 'before going live' clearly situates this tool in the workflow prior to publish_website or making the site live. It gives clear context for when to use the tool, though it does not explicitly name alternatives or exclusions.

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 full burden of behavioral disclosure. It transparently reveals the human-approval requirement, the $1 USDC/month cost, legal verification, and the procedural order of operations. However, it does not disclose what happens after 'claim' (e.g., return value, failure modes, or reversibility), preventing a perfect score.

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 extremely efficient, leading with the purpose and then packing a full workflow into four sentences. Every clause adds value—the human check, cost, legal, conditional steps, and the zip-safety rule together create a compact, well-structured guide without repetition or 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?

For a complex multi-step tool with no annotations and no output schema, the description covers the essential workflow, prerequisites, and safety considerations. It is missing details about error handling, fallback behavior if the human declines, or the tool's return value, but it provides enough for an agent to execute the main path 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, providing a baseline of 4. The description adds context around workflow variables like putUrl and dropUrl, but these are not tool parameters. No additional parameter semantics are needed or possible given the empty 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 description opens with 'Publish a website,' a specific verb+resource statement. It further clarifies its role by outlining a multi-step workflow (upload_url → PUT → inspect → claim) that distinguishes it from siblings like upload_url, inspect, and claim, which are individual steps rather than the orchestrated publishing action.

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, conditional usage instructions: ALWAYS ask human first, with specific questions about cost and legal compliance. It then provides a step-by-step sequence with branching logic ('if you have the zip... else give dropUrl') and a safety rule about never putting the zip in chat. This is far beyond the minimum viability.

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. It mentions a size limit (max 3MB) and instructs to send dropUrl only if no file, but it does not disclose what the tool actually does (e.g., whether it uploads, returns URLs, or requires authentication). The behavior is unclear and potentially misleading.

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 very short and front-loaded with instructions. It is concise, but it omits essential information about the tool's purpose, making it under-specified rather than efficiently concise.

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 tool has no parameters, no output schema, and no annotations, the description is the only source of information. It fails to explain what the tool does, what inputs it expects (e.g., putUrl, dropUrl are not defined), and what the output is. The description is incomplete for an agent to use 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, and schema description coverage is 100% (vacuously). The description does not need to explain parameters since there are none. Baseline 4 is appropriate for a tool with no parameters.

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 is imperative and mentions 'putUrl' and 'dropUrl' but does not clearly state what the tool does (e.g., upload a file via a URL). It assumes prior context and does not name the resource or action explicitly, making it vague for an agent without additional context.

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 some usage guidance: 'If you have the zip, PUT putUrl yourself' and 'Do not put zip in chat', which implies when to use the tool (when you have a zip and a putUrl). However, it does not explicitly contrast with sibling tools or explain when not to use it beyond the zip context.

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