antrieb

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

With no annotations provided, the description carries the full burden. It discloses that the tool performs destructive actions ('destroy', 'decommission', 'drain'), which is critical behavioral context. However, it doesn't mention permissions required, irreversible consequences, or error handling, leaving gaps for a mutation 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?

The description is two concise sentences with zero waste. The first sentence states the purpose, and the second provides parameter-specific usage guidelines. It's front-loaded and efficiently structured.

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 destructive mutation tool with no annotations and no output schema, the description is adequate but incomplete. It covers the purpose and parameter usage well, but lacks details on permissions, side effects, or response format. Given the complexity and risk of deletion, more behavioral context would be beneficial.

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 schema already documents both parameters fully. The description adds minimal value by linking parameters to specific operations (session_id for clusters, image for images), but doesn't provide additional syntax or format details beyond what the schema states. Baseline 3 is appropriate here.

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 specific action (delete/destroy/decommission) and the resources involved (cluster or image), distinguishing it from sibling tools like 'provision' (create), 'save' (preserve), 'exec' (run), and 'search' (find). It uses precise verbs and identifies the two target resources.

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 explicitly states when to use each parameter: 'Pass session_id to destroy a provisioned cluster. Pass image to decommission a custom image and drain its pool.' This provides clear, parameter-specific usage instructions, though it doesn't mention alternatives or exclusions beyond the two options.

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 provided, the description carries the full burden of behavioral disclosure. It helpfully describes the return values (stdout, stderr, exit code) and implies mutation capabilities through examples like 'install packages' and 'configure services'. However, it lacks details on permissions needed, potential side effects, error handling, or rate limits, leaving gaps for a tool that executes shell commands.

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 highly concise and well-structured, with two sentences that efficiently convey purpose, return values, and usage examples without any wasted words. It is front-loaded with the core functionality, making it easy to understand quickly.

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 complexity of executing shell commands (a potentially powerful and risky operation), no annotations, and no output schema, the description is moderately complete. It covers purpose, returns, and usage but lacks critical details like safety warnings, authentication requirements, or output format specifics, which are important for such a 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 description coverage is 100%, so the schema already documents all three parameters (session_id, node, command) adequately. The description does not add any additional semantic details about the parameters beyond what the schema provides, such as format examples or constraints, resulting in a baseline score 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 the specific action ('Execute a shell command on a specific node') and distinguishes from siblings by focusing on command execution rather than deletion, provisioning, saving, or searching. It provides concrete examples of use cases (install packages, configure services, deploy code, verify results) that help differentiate its 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 description provides clear context for when to use this tool ('to install packages, configure services, deploy code, and verify results'), giving practical guidance. However, it does not explicitly state when NOT to use it or mention alternatives among the sibling tools, which prevents a perfect score.

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 provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: it returns specific outputs (session_id, node names, TTL), configures nodes with passwordless SSH and /etc/hosts, and enables inter-node communication by hostname. It does not cover aspects like error handling, permissions, or rate limits, but provides substantial context beyond basic function.

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 front-loaded with the core purpose, followed by return values and configuration details, and ends with a usage guideline. Every sentence adds essential information without redundancy, making it highly efficient and well-structured for its complexity.

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's complexity (provisioning clusters), no annotations, and no output schema, the description is largely complete: it explains the action, outputs, node configuration, and references a sibling tool. It could improve by detailing error cases or TTL behavior, but it covers the essential context for effective use.

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 100% description coverage, so the baseline is 3. The description adds value by explaining the parameter's purpose ('VM topology') and providing examples of shortcuts (e.g., 'ubuntu24.04' expands to a specific string, 'ubuntu24.04 x3' creates multiple VMs), which clarifies usage beyond the schema's technical definition.

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 specific action ('Provision a VM cluster') and resource ('VM cluster'), distinguishing it from siblings like 'delete', 'exec', 'save', and 'search'. It provides concrete details about what is created (nodes with SSH and host configuration) rather than being vague or tautological.

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 explicitly states 'Use exec to run commands on individual nodes', providing clear guidance on when to use an alternative tool ('exec') for related tasks. However, it does not specify when to use this tool versus other siblings like 'delete' or 'save', or any exclusions, so it lacks full alternative coverage.

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 provided, the description carries the full burden of behavioral disclosure. It mentions that Antrieb generates build scripts and documentation automatically, which adds some context about automation. However, it lacks critical details such as permissions required, whether the save operation is reversible, potential side effects, or error handling, leaving significant gaps in transparency for a tool that likely involves mutation.

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 with two sentences that directly address the tool's function and automation aspect. It is front-loaded with the core purpose, and each sentence adds value without unnecessary elaboration, though it could be slightly more structured by explicitly separating usage notes.

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 complexity of saving a node as a custom image (likely a mutation operation), no annotations, and no output schema, the description is incomplete. It fails to cover important aspects like what the tool returns, error conditions, or dependencies on other tools (e.g., requiring a provisioned session first), making it inadequate for safe and effective use.

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 100% description coverage, so the schema already documents all parameters well. The description does not add any additional meaning or context beyond what the schema provides (e.g., it doesn't explain relationships between parameters like 'node' and 'commands'). Baseline 3 is appropriate as the schema handles parameter documentation adequately.

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 action ('Save a node as a reusable custom image') and specifies the resource ('node'), making the purpose understandable. However, it does not explicitly differentiate this from sibling tools like 'delete' or 'provision', which would require mentioning what makes 'save' unique in this context (e.g., persistence vs. deletion or creation).

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 minimal guidance by mentioning that 'Antrieb generates the build scripts and documentation automatically,' which hints at automation but does not specify when to use this tool versus alternatives like 'provision' or 'exec'. No explicit when/when-not scenarios or prerequisites are stated, leaving usage context unclear.

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 provided, the description carries the full burden. It describes the two main behaviors (search images vs list clusters) and mentions default behavior, but doesn't disclose important behavioral traits like rate limits, authentication requirements, pagination, or what happens when no results are found.

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 concise with just two sentences that efficiently convey the tool's purpose and main usage pattern. Every word earns its place, and the information is front-loaded with the core functionality stated immediately.

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 search/list tool with 3 parameters and no output schema, the description covers the basic functionality adequately but lacks details about return format, error conditions, or result structure. The absence of annotations means the description should do more to explain behavioral 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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond what's in the schema - it mentions the default behavior and the clusters option, but doesn't provide additional semantic context about parameter interactions or usage patterns.

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 searches images or lists active clusters, providing specific verbs and resources. It distinguishes between the two modes (images vs clusters) but doesn't explicitly differentiate from sibling tools like 'provision' or 'save' beyond the search/list functionality.

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 clear context for when to use each mode: default lists images, use type='clusters' for active clusters. However, it doesn't mention when NOT to use this tool or explicitly compare it to alternatives among the sibling tools.

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