Deterministic cost estimate across all models for a task, without using a quote from your allowance. Optionally pass expected_output_words.
| Name | Required | Description | Default |
|---|---|---|---|
| description | Yes | ||
| expected_output_words | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint=true), the description adds that it's deterministic and doesn't use allowance. This provides helpful behavioral context not explicitly in annotations, though 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 short sentences convey core purpose, key behavioral trait, and optional parameter. No redundant or ambiguous phrasing.
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 should at least hint at return format (e.g., estimated cost value, currency). It omits that, plus does not explain the required 'description' parameter. Still, it covers core usage adequately.
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% and description only mentions 'expected_output_words' optionally. The required 'description' parameter is completely unexplained, leaving the agent to infer its purpose. This is insufficient.
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: generating a deterministic cost estimate across all models for a task without using allowance. It distinguishes from siblings like quote by highlighting it doesn't use quota, and the verb 'estimate cost' is specific.
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 when to use this tool (when a quick, no-cost estimate is needed vs. quote tool for actual allowance use). However, it lacks explicit when-not-to-use or alternative tool mentions.
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.