Skip to main content
Glama

The world according to capital

Publish a collection

publish_collection
Idempotent

Publish a draft collection: it is indexed, sitemapped and announced to search engines. A curator may publish a draft on its own once it passes the gate and its list fits its name; retiring or renaming a live page stays with Tiago. Refused below 10 bookmarks under its rule, for a category or startups page without its own title, h1, lead and description, and for a startups page without its target_query or with a live page on the same rule. Curator only.

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": {
      "kind": "<kind>",
      "slug": "<slug>"
    },
    "name": "publish_collection"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
slugYesThe page's address, /collections/{slug}: lowercase words joined by hyphens, as people search for it ("yc-fall-2026", "a16z-speedrun-sr008", "defense-tech-startups").

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only say it is a non-read-only, idempotent, non-destructive mutation; the description adds real behavioral context: the page becomes publicly indexed, sitemapped and announced to search engines, and it is curator-only. It also enumerates preconditions and refusal rules (10+ bookmarks, required title/h1/lead/description, target_query for startups pages, no live page on the same rule). What it does not state is whether publishing is reversible or what happens to a page already live under the same slug. The phrase 'announced to search engines' sits in mild tension with openWorldHint=false, but this reads as the platform's own indexing pipeline rather than a true contradiction.

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?

The action and effects are appropriately front-loaded, and no sentence is pure filler. However, the refusal conditions are compressed into a single dense clause-chain full of internal jargon ('the gate', 'its rule', 'stays with Tiago') that is hard to parse on first read and would be clearer as a list.

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 two-parameter mutation with no output schema, the description covers effects, permissions and failure modes well. The remaining gaps are whether publishing is reversible and what a success response confirms, which matter for an agent deciding whether to retry or undo.

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?

The slug parameter is well documented in the schema itself (format, examples), so the description adds little there. Coverage is only 50%, and while the description does hint at kind-specific semantics by referencing 'category or startups page' rules and target_query requirements for startups pages, the yc_batch and speedrun_cohort enum values are never explained anywhere.

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 specific verb and resource (publish a draft collection) and spells out the concrete effects: indexing, sitemapping and search-engine announcement. It also delineates scope by saying that retiring or renaming a live page 'stays with Tiago', which distinguishes this from update_collection-style edits, though it never names a sibling tool outright.

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 clear when-to-use context (a draft that passes the gate and whose list fits its name) plus explicit exclusions (retiring or renaming a live page is not this tool). It also lists refusal conditions, which tells the agent when NOT to call it. It stops short of naming the correct alternative tool for out-of-scope edits, leaving that inference to the agent.

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