Quality guarantee: re-run a completed request once for free if its deliverable scored below 70/100 on the automated quality check. Produces a fresh deliverable with the same accepted quote.
| Name | Required | Description | Default |
|---|---|---|---|
| request_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint=false, destructiveHint=false) are consistent with description. Description adds context: it's free, produces fresh deliverable with same quote. 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, no wasted words. Purpose and condition are front-loaded.
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?
Tool is simple with one param. Description covers condition and outcome. Missing edge cases (e.g., invalid request_id, score above 70) but adequate for basic use.
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 0%, but description does not add meaning for the single 'request_id' parameter beyond type string. It implies it refers to a completed request but gives no format or example.
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 purpose: to re-run a completed request for free if its deliverable scored below 70/100. It specifies the condition and outcome, distinguishing it from siblings like 'accept' or 'estimate_cost'.
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 specifies when to use (when quality check score is below 70/100). It lacks explicit exclusions or alternatives, but the condition is clear. Sibling tools provide context.
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 serves a distinct purpose in the quote-to-deliverable workflow: initiating quotes, accepting, estimating costs, polling results, rerunning with quality guarantee, and checking spending. No overlapping functionality.
All tool names use lowercase with underscores for compound names (e.g., get_deliverable, estimate_cost). Single verbs like quote and spend are also consistent with the pattern.
With 6 tools, the server covers the essential operations for managing AI model quotes and deliverables without unnecessary complexity. The count is well-scoped for a focused service.
The lifecycle from quote to deliverable is well-covered, but a cancellation or rejection tool is missing, which could be needed if a user changes their mind after accepting a quote.