steel_mtr_checkScreen a mill cert's yield and tensile against the specified limits for A992, A572 Gr. 50 or A36 — a screening aid, not acceptance. Published nominal values for estimating and orientation, not design guidance.
| Name | Required | Description | Default |
|---|---|---|---|
| grade | Yes | Steel grade: "A992", "A572 Gr. 50" or "A36" | |
| yield_ksi | Yes | Reported yield, ksi | |
| tensile_ksi | Yes | Reported tensile, ksi |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses the tool is a screening aid using published nominal values, not acceptance or design guidance. However, it does not describe the output format or behavior (e.g., pass/fail result), leaving some ambiguity for a 3-parameter tool.
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?
Description is two sentences, front-loaded with the primary action and purpose. Every clause adds value: 'screening aid, not acceptance' and 'nominal values for estimating... not design guidance' are concise and avoid 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?
For a simple 3-parameter tool with no output schema or annotations, the description explains the purpose and limitations but omits details about what the tool returns or how results are presented. This leaves the agent to infer output behavior, making it adequate but with a clear gap.
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 covers all three parameters (grade, yield_ksi, tensile_ksi) with descriptions. The description adds context by linking yield and tensile to the screening limits and naming specific grades, but does not go beyond the schema's core meaning, so baseline 3 is appropriate.
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 screens mill cert yield and tensile against specified limits for A992, A572 Gr. 50, or A36. The verb 'screen' is specific and the resource is well-defined, distinguishing it from steel-related sibling tools that handle bolt pretension, connections, gauge thickness, plate weight, and shape weight.
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?
Description provides explicit context on when to use (for screening/estimating) and when not to use (not for acceptance, not design guidance). However, it does not explicitly name alternative tools for comparison, though the siblings imply other use cases.
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: lookups (bolt pretension, gauge, pipe, shape), weight calcs (plate, section, shape, takeoff), area calc, reference, MTR screening, and PDF/document generators (NCR, RFI, RFQ, markup). Even the three weight tools are explicitly differentiated by input type, and the descriptions cross-reference each other to avoid confusion.
All tool names share the 'steel_' prefix and follow a 'resource_property/action' pattern (e.g., steel_plate_weight, steel_rfi_generate). However, the suffix is not uniformly a verb or noun: some end with a noun (steel_coating_area, steel_pipe_schedule) and others with a verb (steel_mtr_check, steel_ncr_generate), creating minor inconsistency in the naming convention.
14 tools is well within the ideal 3-15 range for a specialized domain. Each tool covers a distinct need for structural steel estimating and documentation, and the count feels comprehensive without being bloated or redundant.
The tool set provides thorough coverage of the structural steel domain: reference lookups, weight/size calculations, coating area, MTR checking, takeoff rollups, and formal document generation (NCR, RFI, RFQ) plus PDF markup. There are no obvious missing operations for a steel estimating/quality document workflow, and the tools together enable a complete estimating and documentation process.