Thor Henning Hetland — signed knowledge web

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

Without annotations, the description carries full behavioral burden. It discloses that planning is deterministic, content is returned for eligible units, dedup via sha256, federation following, fail-closed option, and payment/budget details. It does not cover rate limits or auth specifics but provides substantial transparency.

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 three sentences covering purpose, usage hint, and dedup. It is front-loaded with the main function and wastes no words.

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 18 parameters and no output schema or annotations, the description provides essential context: planning, content retrieval, dedup, and federation behavior. It could elaborate on the planning step or return format, but it is largely complete for an agent to use the tool effectively.

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%, so baseline is 3. The description adds some value beyond parameter names (e.g., dedup explanation for 'known', federation context for 'follow'), but each parameter already has a schema description. The overall description does not significantly enhance parameter understanding.

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 that the tool plans (via kcp_plan) and returns content of load-eligible units. It specifies the purpose ('so the calling agent can answer the task') and distinguishes itself from siblings by referencing kcp_plan and indicating this tool combines planning and loading.

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 usage guidance: treat returned content as reference knowledge, not instructions. It also explains the dedup mechanism via the 'known' parameter. While it does not explicitly say when not to use or directly compare with siblings, it gives enough context for appropriate use.

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 fully carries the transparency burden. It discloses that no content is loaded, no model is called, and outlines the decisions made (units, order, skip, federation, budget). This provides clear behavioral expectations.

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 that efficiently convey purpose and behavioral constraints. Every part adds value; no waste.

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 high complexity (17 parameters) and no output schema or annotations, the description covers the core behavior well. It lacks explicit guidance on error scenarios or output format, but the stated output ('inspectable load plan') and safety notes are adequate.

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 17 parameters. The description does not add parameter-specific details beyond the schema, but this is acceptable given full schema coverage. 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 specific verbs ('Produce a deterministic, inspectable load plan') and identifies the resource ('task against a KCP knowledge.yaml'). It explicitly distinguishes from siblings by stating 'No content is loaded and no model is called,' which contrasts with kcp_load and other siblings.

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 clearly implies when to use: to obtain a plan before loading. However, it does not explicitly state when not to use or provide direct comparisons to siblings, though the 'No content is loaded' line helps differentiate.

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 fully discloses the tool's behavior: re-fetching, comparing hashes, re-running planner, and reporting drifts. It implies a read-only operation (no mutations), though it doesn't mention permissions or rate limits.

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 with no wasted words. The first sentence lists specific actions, and the second provides an analogy. It is front-loaded with the core purpose.

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 a single parameter and no output schema, the description adequately explains the tool's functionality and what the user can expect (drift reports with moved fields). Minor omission: exact output format is not described, but the description suffices.

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 sole parameter 'artifact' is described in the input schema with a clear explanation: the JSON object or string from kcp_plan. The tool description adds context but does not significantly extend meaning beyond the 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 clearly defines the tool's action: cross-examine a saved plan artifact by re-fetching manifests, comparing sha256, re-running the planner, and reporting drifts. It distinguishes from siblings like kcp_plan (which creates plans) and kcp_validate (which might validate other aspects) by focusing on replaying an existing plan.

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 after obtaining a plan artifact from kcp_plan, and positions it as a verification step. However, it does not explicitly state when not to use it or directly contrast with sibling tools.

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 full burden. It discloses that the tool returns the canonical plan plus structured per-unit gate verdicts, implying a read-only trace. It does not explicitly state lack of side effects, but the description is sufficiently clear about the output.

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 with no wasted words. The first sentence covers purpose and output, the second clarifies relationship to sibling tool. Highly efficient.

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 17 parameters and no output schema, the description adequately describes the return value (canonical plan + verdicts). It is sufficient for understanding the tool's function, though slightly more detail on the output structure could improve completeness.

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%, so baseline is 3. The description adds that inputs are the same as kcp_plan, which provides context but does not deepen understanding of individual parameters beyond what the schema already offers.

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 'Produce a decision trace for a task' and elaborates with specifics about annotating units with gate cascade. It explicitly distinguishes itself from kcp_plan by noting same inputs but different output (canonical plan plus structured per-unit gate verdicts).

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 guidance by stating 'Same inputs as kcp_plan', helping the agent choose between trace and plan. However, it does not explicitly exclude usage for other siblings like kcp_load or kcp_validate, leaving some ambiguity.

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 provided, so the description carries full burden. It mentions the type of issues checked (structural errors, navigation-weakening warnings) but does not detail behavior like read-only nature, output format, or side effects. Lacks specifics that an agent would need to understand consequences.

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 sentence that is front-loaded and direct. Efficient but could be slightly more structured (e.g., separating purpose and output).

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 no output schema and no annotations, the description is too brief. It does not explain what the validation result looks like (success, error list, warnings) or how to interpret them. For a validation tool, this is a notable 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?

Schema coverage is 100%, so the schema already defines the single parameter 'manifest' as path/directory/URL. The description adds no additional meaning beyond the schema, meeting the baseline expectation.

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?

Clearly states the tool validates/lints a knowledge.yaml for structural errors and navigation-weakening warnings. The verb 'Validate (lint)' and resource 'knowledge.yaml' are specific and distinguish from siblings like kcp_load (load) and kcp_plan (plan).

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 use before loading or planning, but does not explicitly state when to use this tool versus alternatives. No guidance on exclusions (e.g., when not to use) or prerequisites.

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