File a quote request with a prototype and R&D machine shop in Grand Rapids, Michigan.
Scored across 2 tools
The two tools are cleanly separated: file_quote_request performs the write action (submitting a quote request), while get_door_schema is an explicitly read-only introspection tool. There is no plausible way to confuse them, and the schema tool even states it 'files nothing.'
Both names follow the same snake_case verb_noun pattern (file_quote_request, get_door_schema) with unambiguous verbs indicating write vs. read. No mixing of conventions.
Two tools is on the thin side even for a narrow inbound 'door' interface; one action plus one schema reader is minimal. It is defensible for a single-purpose intake endpoint, but a status/lookup tool would round it out.
The surface covers submission and self-description, which fits a pure intake door, but there is no way to check the status of a filed request, retrieve a prior submission, or withdraw one. These omissions are understandable for an inbound-only endpoint but are still notable gaps.
File a quote request with Cyclone Machining Co. (Grand Rapids, Michigan): prototypes, first articles, one-offs, revisions, replacement parts with or without a drawing, small runs. A person reads every request before anything is priced. Set review_only for a free engineer's review without a quote; set export_controlled when the part's data may be controlled.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | required, the person | |
| agent | No | optional, the name and version of the agent filing this | |
| Yes | required, where the shop's reply goes | ||
| files | No | optional, [{name, bytes}] - names only; the answer to the request says where to send the files (no file link when export_controlled is yes or not sure) | |
| company | No | optional | |
| material | No | optional, e.g. 6061 aluminum, 17-4 stainless, titanium, Inconel 718 | |
| quantity | No | optional, one is normal here | |
| needed_by | No | ISO date | |
| sent_back | No | optional, true when another shop sent the job back | |
| no_drawing | No | optional, true when the part itself is the drawing | |
| description | Yes | required, up to 8,000 characters: what the part does, what to hold, what exists (a STEP, a PDF, a broken sample) | |
| review_only | No | optional, true to ask for a free engineer's review of the part: no quote is sent unless asked | |
| sent_back_reason | No | optional, up to 500 characters: why it was sent back (a reason alone marks the request as sent back) | |
| export_controlled | No | optional, one of no, yes, not sure: whether the part's data is export-controlled (ITAR or EAR). Yes or not sure: the answer gives no file link, and no files or controlled detail are sent until a person arranges a controlled channel |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a non-read-only, open-world, non-destructive write, so the description's job is to add context. It does: 'A person reads every request before anything is priced' discloses the human-in-the-loop review gate, and the export_controlled note states the concrete consequence (no file link, no files or controlled detail transmitted until a controlled channel is arranged). It does not address duplicate filings/idempotency, so it is not exhaustive.
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 dense sentences with no filler; the shop identity and accepted job types come first, then the two behaviorally significant flag semantics. Every clause carries information an agent needs.
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?
For a 14-parameter submission tool with no output schema, the description covers the two non-obvious flags and the human review process, and the files schema field explains where the file-sending instructions arrive in the answer. Missing pieces are minor: turnaround expectations and what happens after the request is filed.
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 the schema already documents all 14 parameters in detail. The description's notes on review_only and export_controlled largely restate what the schema descriptions already say, adding only slight reinforcement rather than new syntax, formats, or defaults. Baseline 3 is appropriate when the schema does the heavy lifting.
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?
States a specific verb and resource ('File a quote request with Cyclone Machining Co.') and immediately scopes the work types accepted (prototypes, first articles, one-offs, revisions, replacement parts, small runs). An agent knows exactly what this tool submits and to whom; the only sibling, get_door_schema, is unrelated so no differentiation burden exists.
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 tells the agent which job types belong here and when to set review_only (free review, no quote) versus a normal quote filing. It gives clear positive conditions but no explicit exclusions or alternative routing, so it stops short of full when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the door's schema: the fields a quote request takes, what comes back, and the MCP and A2A notes. Reads only; files nothing.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description's 'Reads only; files nothing' restates rather than extends that. It does add genuinely new behavioral context by scoping what the returned schema documents, including the non-obvious MCP and A2A notes, which helps an agent decide whether the call is worth making.
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, front-loaded with the return content, and the operational caveat ('Reads only; files nothing') placed last. No filler or redundancy.
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?
There is no output schema, so the description carries the burden of describing the return, and it does so by enumerating the schema's parts (request fields, response fields, MCP/A2A notes). With annotations covering safety and no parameters to document, the only minor gap is the absence of any hint about how the schema is structured or how large it may be.
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 tool takes zero parameters and schema coverage is 100%, so the baseline of 4 applies; there is nothing for the description to disambiguate. No parameter-level semantics are needed or missing.
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?
States a specific verb (Return) and resource (the door's schema) and enumerates what the schema contains: quote-request fields, response fields, and MCP/A2A notes. It implies its distinction from file_quote_request with 'files nothing' but never names that sibling explicitly, so differentiation is present yet not fully explicit.
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 phrase 'Reads only; files nothing' points away from the write-oriented sibling file_quote_request, implying this is the discovery step before filing. However, it never states when to call this versus the sibling (e.g., 'call this first to learn the request shape'), leaving usage to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
file_quote_requestget_door_schemaGet 3D printing and manufacturing quoted by a person, shipped anywhere in the US.
Turn designs into shipped parts: quote 3D printing, CNC, and decals, then check out.
Instant 3D printing and CNC machining quotes from your CAD files (STL, STEP, 3MF, OBJ): price and ship date for SLS nylon, FDM plastic, aluminum and brass parts made in the US
Quote, check and order 3D prints of STL, 3MF, STEP or OBJ files. Made in the USA, shipped in the US.
Add one secure layer between your agents and this server.
