Korext: AI Code Governance

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

No annotations are provided, so the description must carry the full burden. It discloses return values (severity, governance context, line numbers) but does not explicitly state whether the operation is read-only, requires auth, or has side effects. Since 'check' implies non-destructive, this is adequate 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?

The description is a single, front-loaded sentence that provides the action, target, and output in a concise manner. No redundant words or 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?

The tool has no output schema, so the description's mention of the return value (violations, severity, context, line numbers) is essential. It covers the main purpose and output adequately. However, given there are no annotations, it could also benefit from a note about read-only behavior or prerequisites, but for a check tool this is sufficient.

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% (both code and packId have descriptions). The description adds minimal semantic value beyond the schema, only hinting at 'one or more' policy packs. According to the baseline for high schema coverage, this scores a 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 uses a specific verb ('Check') and clearly identifies the resource ('code snippet' against 'policy packs'). It distinguishes itself from sibling tools like generate_proof or list_packs, which serve different purposes.

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 implies its usage (checking code against policy packs) but does not explicitly state when to use it over alternatives or mention exclusions. Sibling tools are clearly different, so context is implied, but no real guidance is 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 full burden. It discloses the return values and the fact that the bundle is cryptographically signed, adding helpful context. However, it does not disclose potential side effects like persistence, storage, or whether the scan is executed remotely, which would be valuable for a proof generation 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 sentences, front-loading the primary action and then listing the output fields. It is succinct, with no redundant information or fluff, making it easy for an agent to parse 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 there is no output schema and no annotations, the description does a good job of conveying the tool's purpose and return values. It clearly states what the agent will receive (bundle ID, decision, violation count, verification URL). However, it lacks explicit error handling or differentiation from sibling tools like check_code, so it is not fully complete but is reasonably sufficient for a tool of moderate complexity.

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 all parameters already have descriptions. The tool description adds minimal extra meaning beyond reaffirming policy packs and the output bundle. It does not elaborate on how parameters like fileName or language affect the scan, but the baseline of 3 is appropriate since the schema handles the heavy lifting.

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 a specific action and resource: scanning code against policy packs and generating a cryptographically signed proof bundle. It distinguishes itself from siblings by emphasizing the generation of a proof bundle with specific return values, which differs from check_code or get_proof.

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 implies when to use the tool (when a signed proof bundle is needed from scanning code) but does not explicitly mention alternatives or when not to use it relative to siblings like check_code or get_proof. The usage context is clear enough, but explicit exclusions are missing.

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 must carry the full burden. It does disclose the output nature (rules with governance context) and the 'living standards' aspect, which is useful. However, it does not explicitly state that it is a read-only operation with no side effects, nor does it mention any auth requirements or rate limits. The verb 'Get' implies read-only, but an explicit statement would be clearer.

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 a single, efficient sentence that front-loads the core purpose and packs in relevant details (enriched directives, governance context, inference enforcement) without any filler. Every word 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 a simple tool with one optional parameter and no output schema, the description adequately explains what the tool returns and in what context it is used. It mentions the inclusion of governance references (CWE, MITRE, regulatory) which helps an agent understand the output. The only minor gap is lack of explicit note about the default packId behavior, but that is already in the 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 input schema already covers 100% of the parameter meaning, including the oneOf string/array type and the default value 'web'. The description merely confirms 'one or more policy packs', adding no additional semantics beyond what the schema provides. The baseline of 3 applies because the schema does the heavy lifting.

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 verb 'Get' and the resource 'enriched policy directives and living standards', specifying the scope 'for one or more policy packs' and the return value 'rules with governance context'. This distinguishes it from sibling tools like list_packs, which likely lists available packs, and check_code, which analyzes code.

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 implies when to use this tool: to retrieve policy directives for packs at inference time enforcement. It does not explicitly exclude alternatives or name sibling tools, but the context 'for inference time enforcement' provides clear usage context. Since list_packs presumably handles pack discovery, get_directives is appropriately positioned for fetching directives.

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 indicates a read-only operation via "Retrieve" and discloses the return contents (decision, violations, packs, verification status). It does not mention error behavior or side effects, but for a get operation this is reasonably transparent.

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 (two sentences), front-loaded with the action, and lists the return contents efficiently. Every word earns its place with no redundancy.

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 get-by-ID tool with one parameter, no annotations, and no output schema, the description clearly states the input and the components of the result. It could have mentioned behavior when the ID is not found or explicitly stated it does not modify data, but given the simplicity, it is mostly 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 provides 100% coverage with a description for bundleId ("The proof bundle ID (kpb_...)"). The tool description adds no additional parameter semantics beyond what the schema states, so 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 uses a specific verb ("Retrieve") and resource ("proof bundle by ID"), clearly distinguishing from siblings like generate_proof (creation) and list_packs (listing). This leaves no ambiguity about what the tool 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 implies usage when an existing bundle ID is available and a fetch is needed, but it does not explicitly mention when to use alternatives or provide exclusion criteria. The contrast with generate_proof is implied but not 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?

With no annotations, the description must carry the full burden of behavioral disclosure. It states that the tool lists available policy packs, implying a read-only operation, but it does not explicitly note the absence of side effects, authentication requirements, or response details. The description is not misleading, but it leaves some behavioral aspects implicit.

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 a single, concise sentence that conveys the essential purpose without unnecessary words. It is well-structured and front-loaded, with no wasted 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 simple list operation with only two optional filters and no output schema, the description is sufficiently complete. It clearly communicates that the tool returns available policy packs with tags, aligning with the sibling tools' context without needing extensive elaboration.

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 provides full descriptions for both parameters (region and industry), achieving 100% schema coverage. The description itself adds no additional parameter semantics beyond what the schema states, so it meets the baseline for high 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 states the tool's action ('List available policy packs') and its scope (with industry and region tags). The verb and resource are specific, and it distinguishes this from sibling tools like check_code or generate_proof, which serve entirely different purposes.

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 does not mention any specific use cases, prerequisites, or situations where another sibling tool might be more appropriate. This leaves the agent to infer usage from context.

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