Rank a CALLER-PROVIDED list of MCP tools by worst-regret if they act, with a signed receipt. Cannot auto-discover the inventory -- MCP does not allow that; the caller must pass it in.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | ||
| inventory | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
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 takes a caller-provided list, ranks by worst-regret, and produces a signed receipt. It also explains the limitation about auto-discovery. It lacks details like whether it is read-only, but overall is fairly transparent for a tool that produces a receipt.
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 action, and wastes no words. It efficiently conveys the tool's purpose and a key constraint.
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 (ranking by regret, producing a receipt) and presence of an output schema, the description could have explained what 'worst-regret' means or the format of the receipt. It provides adequate context but leaves some ambiguity 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 description coverage is 0%, and the description does not explain the individual parameters. The 'inventory' parameter is implied as a list of MCP tools but no structure or required fields are specified. The optional 'notes' parameter is not mentioned. The description fails to compensate for the lack of schema documentation.
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 the tool ranks a caller-provided list of MCP tools by worst-regret with a signed receipt. It is specific, uses a verb (rank) and resource (list), and distinguishes from sibling tools that mint or verify receipts, though not explicitly differentiated.
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 explains that the tool cannot auto-discover inventory, so the caller must pass it in, which helps set expectations. However, it does not provide explicit guidance on when to use this tool versus alternatives or state 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.
Add one secure layer between your agents and this server.
Each tool targets a distinct purpose: auditing tool risk, minting generic receipts, minting CRM-specific receipts, and verifying receipts. Descriptions clearly differentiate inputs and outputs, minimizing confusion.
All tools follow a verb_noun pattern with underscores (audit_*, mint_*, mint_*, verify_*), maintaining a consistent style. The nouns are descriptive of the specific functionality, ensuring clarity.
Four tools is a well-scoped set for a specialized receipt management and auditing server. Each tool serves a distinct role without unnecessary bloat.
The tool set covers creation of receipts (generic and specific), verification, and an inventory auditing feature. This appears complete for the server's stated purpose with no obvious gaps.