Cantara wiki — community knowledge web

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

No annotations provided, so the description carries full burden. It discloses dedup behavior and the nature of returned content, but omits error handling, authentication, 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?

Three sentences, front-loaded with purpose, then guidance, then dedup note. Compact and efficient, though could be better structured with bullet points.

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 18 parameters, no output schema, and no annotations, the description is too brief. It does not explain 'load-eligible units', planning details, output format, or failure modes, leaving significant gaps for the agent.

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 value by explaining the 'known' parameter's dedup logic, but does not elaborate on other parameters beyond 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 states the tool plans and returns content of load-eligible units. It distinguishes from siblings only by mentioning 'as kcp_plan', but does not contrast with kcp_replay, kcp_trace, or kcp_validate.

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?

Provides guidance on treating returned content as reference and using the 'known' parameter for dedup. However, it lacks explicit direction on when to use this tool over siblings or alternatives.

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 discloses determinism, inspectability, and that no content is loaded or model called, which implies read-only behavior. However, it does not explicitly mention authentication needs, rate limits, or side effects beyond the plan generation.

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-loaded with the core purpose, and every word adds value. There is no redundancy or unnecessary detail, making it highly concise and well-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?

Given 17 parameters, no output schema, and no annotations, the description provides a reasonable overview of what the plan includes (units, order, skip reasons, etc.). It lacks details on return format or edge cases, but sufficiently covers the essence for an agent to understand the tool's purpose and constraints.

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 baseline is 3. The description adds a high-level overview but does not provide specific parameter meanings beyond what is already documented in the schema. No additional value is gained from the description for 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 it produces a deterministic, inspectable load plan for a KCP knowledge.yaml, specifying what it includes (units order, skip reasons, federation, budget) and explicitly distinguishes from loading content by stating 'No content is loaded and no model is called.' This differentiates it from sibling tools like kcp_load.

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 to plan knowledge retrieval, but does not explicitly state when to use or not use alternatives. The 'No content is loaded' phrase helps agents understand this is a planning step, but more direct guidance would improve clarity.

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 fully discloses behavior: re-fetching manifests, comparing sha256, re-running the pure planner, and reporting drift with moved fields. No contradictions.

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, each packed with relevant information. No fluff. The first sentence explains the operation, the second provides context. Efficient and well-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?

Despite no output schema, the description explains what is returned (identical or drifted per manifest with fields). It covers the key behavioral steps, making the tool's behavior complete for an AI agent.

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% and describes the artifact parameter as the JSON from kcp_plan. The description adds no additional semantic detail beyond that, but it is sufficient given the schema's clarity.

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 vivid analogy ('cross-examine') and specifies actions: re-fetch, compare sha256, re-run planner, report drift. It clearly identifies the input (plan artifact) and output (drift report with fields), distinguishing it from sibling tools like kcp_plan which generates the artifact.

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 contrasts 'plan is evidence; replay is cross-examination', providing clear context. No explicit when-not-to is stated, but the purpose is clear enough.

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 description carries full burden. It discloses the output includes per-unit gate verdicts across multiple gates (audience, temporal, budget, etc.) and that it uses the same inputs as kcp_plan. It does not explicitly state read-only nature or side effects, but the trace purpose implies non-destructive behavior.

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 concise sentences: first states purpose, second provides relationship to sibling and output details. No redundant words, front-loaded with key 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?

Given 17 parameters and no output schema, the description adequately explains the tool's purpose, output, and relationship to kcp_plan. It does not address potential performance impact or permission requirements, but is mostly complete for a trace/analysis 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 baseline is 3. The description adds minimal parameter meaning beyond the schema; it only mentions that inputs are same as kcp_plan and lists evaluated gates, not 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?

Description clearly states 'Produce a decision trace for a task' and explains the output annotates each unit with gate cascade verdicts. It also distinguishes from siblings by noting 'Same inputs as kcp_plan; returns the 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 implies usage when detailed gate-level verdicts are needed beyond the plan, and hints at similarity to kcp_plan. However, it does not explicitly state when not to use or compare to other siblings like kcp_load, kcp_replay, or kcp_validate.

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 convey behavioral traits. It mentions the types of issues found (structural errors and warnings) but omits side effects (read-only), authentication needs, or failure behavior. Adequate but not detailed.

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 core purpose without unnecessary words. It could be slightly improved by front-loading key aspects, but current structure is 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 the tool has one parameter and no output schema, the description explains what it does but does not specify return value format or how results (errors/warnings) are presented. This is a gap for a linting 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?

The input schema has 100% description coverage, explaining the 'manifest' parameter as a path/directory/URL. The description adds no extra information beyond the schema, 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 clearly specifies the action (validate/lint), the resource (knowledge.yaml), and what is checked (structural errors and navigation-weakening warnings). It distinctly identifies the tool's purpose, differentiating it from sibling tools like kcp_load and kcp_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 the tool is for validating knowledge.yaml files but provides no explicit guidance on when to use it versus alternatives (e.g., before kcp_load). It lacks context on prerequisites 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.