Skip to main content
Glama

write_cdif

Writes a CODATA CDIF JSON-LD description for a published Semantic Data Charter model from a catalog ID or local package, citing schema URL/SHA-256 and validating output with CDIF checks.

Instructions

Write the CODATA CDIF description (JSON-LD: Discovery, Data Description with every variable, Codelists, and the sentinel domain for the sixteen exceptional values) of one published Semantic Data Charter model. The document cites the model's schema by URL and SHA-256. Validated in this package's CI with CDIF's own framing, JSON Schema and SHACL checks from a pinned snapshot.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "write_cdif"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoThe catalog date, YYYY-MM-DD; today when omitted.
ct_idNoThe model's identifier (CUID2) in the public catalog; the package is fetched from the host this server was started with.
directoryNoA package directory already on disk (dm-<ct>.jsonld and dm-<ct>.xsd, optionally catalog.json and versions.json). Give this or ct_id, not both.
contact_nameNoThe publisher's contact point name; the package's declared default applies when omitted.
contact_emailNoThe publisher's contact e-mail; the package's declared default applies when omitted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv4.1.1

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations at all, the description carries the full burden. It does disclose real behavior beyond the signature: the document embeds the model schema's URL and SHA-256, and the output is validated against CDIF framing, JSON Schema and SHACL from a pinned snapshot — useful provenance. But it never says where the document is written, what is returned, what happens on validation failure, whether it re-fetches, or whether it requires network/auth access to the host the server was started with.

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

Conciseness4/5

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

Three sentences, front-loaded with the artifact produced, followed by provenance and validation guarantees in descending order of importance. The long parenthetical enumerating the document's sections is information-dense rather than wasteful, though the SHACL/framing clause borders on audience-specific noise.

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

Completeness3/5

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

For a five-parameter write tool with no annotations and no output schema, the definition establishes what is produced and how it is verified, but omits what an agent needs to plan a call: the return value/success signal, the failure mode when validation rejects the document, and where the artifact lands. Adequate, not complete.

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

Parameters3/5

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

Schema description coverage is 100% and every parameter carries its own explanatory text, so the schema does the parameter work. The description adds no parameter-level meaning beyond noting that the document cites the model's schema by URL and SHA-256, which is output behavior rather than argument semantics. Baseline 3 applies.

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

Purpose4/5

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

The description gives a specific verb ('Write') and a precisely scoped resource: the CODATA CDIF/JSON-LD description of one published Semantic Data Charter model, enumerating the document's contents (Discovery, Data Description, Codelists, sentinel domain). An agent can tell what artifact is produced, though the density of domain jargon (CDIF, SHACL, framing) assumes a specialist audience. No siblings exist to differentiate against.

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 only implied: the tool applies to 'one published Semantic Data Charter model', suggesting this is the step for producing a publication-ready description. There is no explicit when-to-use, when-not-to-use, prerequisite (e.g. a validated model must exist first), or ordering guidance relative to other steps. The mutual exclusivity of ct_id vs directory is stated in the schema, not here.

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

Deploy Server

Other Tools