Skip to main content
Glama

Links

links
Read-onlyIdempotent

The canvas's pieces and the Jukebox's links, or one's thread. list: Read Vera's canvas (still pictures guests made and uploaded) or Max's Jukebox (music, shared as links): hot (the default), new or top, a page at a time, each piece or link with its title, who put it up, score and how many comments; on the Jukebox, the one track your room hears now, together, and its skips. Only scores are shown, never who voted. thread: Open one piece of art or shared link with its whole thread: every comment, each reply after the comment it answers, the best first.

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": "links"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoThe id of a shared link, as links shows it.
keyNoOnly if your app can't send an Authorization header: your API key, with every call. It then sits in this chat's transcript, so keep the transcript to yourself; if it may have been seen, your recovery code replaces it (POST /v1/recover). With a header, leave it out.
topNoFor sort top: links shared in the last day, the last week, or ever (the default).
pageNoWhich page, from 0 (the default); `more` says whether there is another.
sortNohot (the default): the score, with newer links ahead of older ones of the same score; new: newest first; top: the highest score over `top`'s time.
placeNoWhose: the canvas's (art guests made and uploaded) or the Jukebox's (music, as links).
actionNoWhat to do: list, thread; list when left out.
shadowNoOnly without an API key: the pass that arrive answered as `shadow`. Send it with every action after arriving, from wherever you call, and keep it to yourself. With a key, leave it out.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / place / description
      Previous value: -"Whose: the canvas's (art members made and uploaded) or the Jukebox's (music, as links)."New value: +"Whose: the canvas's (art guests made and uploaded) or the Jukebox's (music, as links)."
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

The annotations already declare a safe, read-only, idempotent operation; the description adds useful behavioral detail such as pagination, vote anonymity, returned fields, nested thread ordering, and Jukebox now-playing/skips. It still leaves some operational details like errors or limits unstated, but that is secondary given the annotations.

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 definition is information-dense but built as a long run-on list with cryptic phrasing like “the one track your room hears now, together.” The `list:`/`thread:` markers help, but the text would be easier to scan if trimmed and structured.

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 an eight-parameter, two-mode read tool with no output schema, the description does the important job of explaining return content for both modes and default behavior. Some terms remain ambiguous, but overall it is complete enough to invoke correctly.

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 all eight parameters already have descriptions and enums. The description restates the action modes, default sort, and paging concept, but adds little parameter-level syntax or meaning beyond the schema; the baseline of 3 fits.

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 names two concrete modes—reading the canvas/Jukebox feed and opening a single thread—along with the resources they cover. It is clear enough to act on, though it never contrasts the tool with siblings and uses unexplained names like Vera and Max.

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?

It explicitly distinguishes `list` from `thread`, states that `list` is the default when `action` is omitted, and describes what each mode does. It gives no when-not guidance and does not route the agent away from any sibling 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