Skip to main content
Glama

Create embed set

create_embed_set

Put a list of a project's terms and claims on other sites under ONE link (PM-1167) — for an article that cites many: the site puts 'script' in once and marks its words by name, or data-kaiku-claim="thm:d5-rank5", each opening its cloud. Only what the list names goes out, each thing as its own link would show it; a name not on it says so and nothing of the project. The list is given by hand: 'terms' — ids, words or spellings — and 'claims' — ids or labels — comma-separated, each one you may put out alone (a confirmed term you may open); the first that is not is the refusal and nothing is made. At most 200 things a set and 20 sets a project. A set has no card. 'sites', 'days' and 'lang' as for create_term_embed. Only for somebody who may write in the project; a line in its history.

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": {
      "project": "<project>"
    },
    "name": "create_embed_set"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoDays the link answers, 1 to 3650. Optional: none is until it is removed.
langNoThe language the link shows the words in, e.g. 'en' (PM-1373): a person's translation where there is one, else the machine's, marked as such. Optional: none shows them as written; a page may still ask for another.
sitesNoSites that may show it, comma-separated, as https://example.org. Optional: none is any site.
termsNoTerms, comma-separated: ids, words or spellings.
titleNoThe set's name, e.g. the article's; up to 120 characters. Optional.
claimsNoClaims, comma-separated: ids or labels.
projectYesThe project key, e.g. MATH.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / lang
      Added value: +{
      +  "default": null,
      +  "description": "The language the link shows the words in, e.g. 'en' (PM-1373): a person's translation where there is one, else the machine's, marked as such. Optional: none shows them as written; a page may still ask for another.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  2. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only cover safety flags, and the description adds real behavioral context: limits are disclosed, the operation is atomic ('the first that is not is the refusal and nothing is made'), exposure is scoped ('Only what the list names goes out'), unknown names leak nothing, and it writes a history line. Some phrasing ('A set has no card') is opaque and leaves a gap in what the agent understands.

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?

It is information-dense and mostly front-loaded, but the prose is a run-on of em-dash fragments and embedded HTML ('<span data-kaiku-term="kernel">') that interrupts the primary instruction. Reordering the batching purpose ahead of the embedding markup would improve scanability.

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?

For a 7-parameter mutation with no output schema, the definition covers limits, atomicity, permissions, and the successful side effect (a history line). What it omits is the return shape — the agent is not told what the created link/identifier looks like in the response.

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 coverage is 100%, so the schema already documents every parameter. The description restates 'terms' as ids/words/spellings and 'claims' as ids/labels, which largely duplicates the schema, though the 200-item cap and the pointer to create_term_embed for 'sites'/'days'/'lang' add marginal value. Baseline 3 is appropriate.

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?

States a concrete verb and resource: putting a list of a project's terms and claims on other sites under one link, with the limits (200 things, 20 sets) that define the object. It implicitly distinguishes itself from create_term_embed/create_claim_embed by being the batch form ('each thing as its own link would show it'), though it never names those siblings directly.

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

Usage Guidelines4/5

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

Gives a use case ('for an article that cites many'), a permission prerequisite ('Only for somebody who may write in the project'), and delegates the 'sites'/'days'/'lang' semantics to create_term_embed. It does not explicitly say when to prefer create_term_embed or create_claim_embed over this batch form, so the alternative routing is left to inference.

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