Skip to main content
Glama

Search parts

search_parts
Read-onlyIdempotent

Find fasteners in the buyer's catalogue from free-text part descriptions, returning interpreted attributes and ranked matches with scores to confirm thread, length, grade, and finish.

Instructions

Find fasteners in the buyer's company catalogue from free text such as "M8x30 SS hex bolt" or "m10 x 50 8.8 zinc". Understands thread/length, stainless grades (A2=304, A4=316, SS=either), steel grades, finishes and head types. Returns the interpreted attributes plus up to limit ranked matches with a 0-1 score and which attributes matched. Thread and length must match exactly. Score below 1 means some attributes differ: tell the user what differs rather than assuming it is acceptable.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_parts"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYesFree-text part description from the buyer or RFQ line
filtersNoExplicit attributes; these override anything parsed from the query

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.2/5.0
Behavior4/5

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 goes beyond them by disclosing the return shape, the 0-1 match score semantics, and the hard rule that thread and length must match exactly. It also gives an explicit handling instruction for imperfect matches, which is real operational context rather than restated annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, followed by parsing scope, return shape, and the matching rule, in five sentences with no filler. Every sentence adds information an agent needs to select and act on results correctly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries return-value explanation and does so adequately (interpreted attributes, ranked matches, score, matched attributes). The main residual gap is the unmentioned `filters` override parameter and unstated behavior on zero matches, both minor for a read-only search tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, and the description compensates well for the most important parameter by explaining what the free-text parser understands (thread/length, A2=304, A4=316, SS=either, grades, finishes, head types) and by capping results at `limit`. It does not mention the `filters` object at all, so the override behavior described only in the schema is left unmentioned in prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Find fasteners in the buyer's company catalogue') plus the input form (free text), and gives two concrete example queries. An agent can distinguish this from get_product or check_availability without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the examples and by the input mode (free text from a buyer or RFQ line), and the closing instruction tells the agent how to act on a sub-1 score. However, the description never states when to prefer this over a direct lookup such as get_product, nor any prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.