Skip to main content
Glama

The Cable Code

Read a tender document: cables built, requirements, schedule, conflicts and gaps

read_tender
Read-onlyIdempotent

Read a project or tender document (a purchase or project specification, a tender volume, a GTP / data schedule; a PDF of up to 80 pages and 20 MB, or its text) and answer what it asks for: every cable it lists built as a design by the designer's rules and checked against its rule set, the required / offered schedule beside the document's own required values with their pages, each requirement mapped to a requirement card or listed as having none, the conflicts (one parameter with two values, a printed construction against a requirement, a value against the standard the document names, a voltage outside IEC 60038, a schedule row with no construction) and the missing sections. An LLM (Claude) copies the document's values and pages; it decides nothing: every design, check, conflict and gap is the deterministic rules with their sources. A reading takes up to a few minutes, so the call starts a job and answers a poll link; the reading is held in memory for one hour, then gone, and the file is never stored. The poll answer (thecablecode.tender/v1) has job, status (running, done or failed), pages and, when done, the reading; a failed paid reading starts again with the same file at no charge, and the same file within the hour is the same job, not charged twice. For one cable use design_cable or check_cable; for one maker's datasheet, extract_datasheet. Here the document's text; a PDF goes to POST /api/v1/tender. Always paid: $4.00 up to 20 pages, $2.00 for each further 10 pages begun, up to 80 pages.

Input Schema

NameRequiredDescriptionDefault
hintNoA cable tag or a voltage to look for first.
langNoThe language of the schedule's parameter names: any of the site's 15 (en, tr, de, nl, sv, fr, es, da, no, fi, it, ro, pl, cs, ru). Default en.
textYesThe document's text (a Word file turned into text); it counts one page per 1,700 characters begun.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare only readOnly/openWorld/idempotent, and the description adds the traits that actually govern invocation: it is a long-running job that returns a poll link, results live in memory for one hour then disappear, the file is never stored, and the poll payload shape (thecablecode.tender/v1, job/status/pages/reading) is named. It also discloses pricing tiers, the 80-page/20 MB ceiling, free retry of a failed paid reading, and de-duplication of the same file within the hour.

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

Conciseness3/5

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

Nearly all content is load-bearing, but it is delivered as one semicolon-chained sentence that forces the reader to parse async behavior, output shape, and pricing in a single pass. Splitting into short labeled clauses (scope / behavior / routing / cost) would preserve the content and cut scan cost; nothing should be removed, only restructured.

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

Completeness5/5

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

For an asynchronous, paid, open-world tool with three inputs, the description covers what is produced, how it is delivered, how long it persists, what failure costs, input limits, and sibling alternatives. No output schema exists, and the poll response fields are described inline, so nothing an agent needs before calling is missing.

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 100% and the schema already explains hint and lang, so the baseline is 3. The description adds meaning the schema cannot: page counting is 1,700 characters per page and PDFs must be routed to the POST endpoint rather than passed in text, which directly affects how the caller fills the required text parameter.

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 ('Read a project or tender document') and enumerates exactly what the answer contains: cables built as designs, requirement mapping, conflicts, and missing sections. It explicitly separates itself from siblings ('For one cable use design_cable or check_cable; for one maker's datasheet, extract_datasheet'), so an agent can route without opening any schema.

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

Usage Guidelines5/5

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

Gives explicit routing rules to alternatives and the condition that selects each: design_cable/check_cable for a single cable, extract_datasheet for a maker's datasheet. It also states the input-mode split ('Here the document's text; a PDF goes to POST /api/v1/tender'), which is the main way an agent would otherwise misuse this tool.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources