Natural-language explanation of a plan_id (what it does) or setting_path (what one setting controls). Audience: merchant (default), developer, or reviewer. Detail: brief (1-2 sentences) or deep (full context + related settings + a11y notes). Use when merchant asks 'what does this do' or 'why this preset'.
| Name | Required | Description | Default |
|---|---|---|---|
| detail | No | ||
| plan_id | No | ||
| audience | No | ||
| setting_path | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses the output form (natural-language explanation), detail levels including deep content ('full context + related settings + a11y notes'), and audience variants. It implies read-only behavior, though it doesn't explicitly state side effects or auth requirements.
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 tightly scoped sentences, each adding distinct information: resource types, audience/detail options, and trigger examples. No filler or repetition.
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, the description states the return type ('natural-language explanation') and covers optional parameters and use cases. The sibling context and absence of required parameters make this 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 description coverage is 0%, so the description must compensate. It does: plan_id is defined as 'what it does', setting_path as 'what one setting controls', audience includes 'merchant (default), developer, or reviewer', and detail is explained as 'brief' vs 'deep' with content. This fully covers all 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 opens with a specific verb and resource: 'Natural-language explanation of a plan_id... or setting_path...'. It clearly distinguishes from sibling tools by naming the exact objects and output type.
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?
It explicitly states when to use: 'Use when merchant asks "what does this do" or "why this preset".' It also provides audience and detail context. However, it does not mention when not to use or name alternatives, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: browse catalogs, diagnose issues, explain plans/settings, generate plans from intent, and provide recommendations. While plan and recommend both generate plans, their inputs and use cases are explicitly separated (direct intent vs. proactive scenarios), eliminating ambiguity.
All tool names are single imperative verbs (browse, diagnose, explain, plan, recommend), following a uniform and predictable naming pattern. There is no mixing of conventions or stylistic inconsistencies.
With 5 tools, the server is well-scoped for its purpose as a planning and recommendation engine. Each tool earns its place, covering discovery, diagnostics, explanation, and planning without unnecessary bloat.
The tool set references critical preview/execute operations (preview() and execute()) that are not exposed as tools, leaving a dead end where plans cannot be applied. Additionally, there is no way to fetch full details for a specific catalog item beyond the paged browse results, making the workflow incomplete.