Skip to main content
Glama

CarlNotes

Suggest Topics

suggest_topics
Read-only

When the user asks to send, share, save, add, or forward something to Carl, CarlNotes, or their Topics without naming a Topic, with phrases like send this to Carl or save this to my topics, call this before send_to_topic and wait for their choice. A named Topic goes straight to send_to_topic. Never call it on your own initiative. Takes the send's title, summary, and links and stores nothing. Preserve an available conversation URL in optional chat_url for the final send. That private reference is excluded from matching and public links. For Codex, preserve codex://threads/ when the actual local thread ID is available. Never invent an ID or create a shared conversation link automatically. Returns every Topic you can edit for sending, strongest matches first and recommended, with weaker editable Topics available unchecked. Lists five Topics per page using list_topics cursors; repeat the same content and optional name query with nextCursor. The MCP Apps view supports name autocomplete, filtering, checkboxes, the standard numbered paginator, live selected-topic tag pills, and one explicit send to all selected Topics. View autocomplete uses autocomplete=true for name-only reads without content matching. It shows Steeping only in the results area without changing view height; the header, search, selection, and standard action buttons stay visible. Text-only hosts receive numbered choices. Every page offers Start a new topic for this chat: only after the user picks it, use the existing suggest_sources and create_topic Topic Draft flow and limits, preview a private draft, and create only after confirmation. Both routes search editable destinations; switch to /mcp to send to another Topic from a Topic-bound connection.

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": {
      "title": "<title>",
      "summary": "<summary>"
    },
    "name": "suggest_topics"
  }
}

Input Schema

NameRequiredDescriptionDefault
linksNo
queryNo
titleYes
cursorNo
summaryYes
chat_urlNo
autocompleteNoCard-only editable Topic-name autocomplete. Skips content matching and stores nothing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true/destructiveHint=false, and the description reinforces this with 'stores nothing' and by explaining that chat_url is excluded from matching and public links — genuinely useful context beyond the annotations. It also discloses return ordering (strongest matches first, recommended, weaker editable Topics unchecked) and pagination via list_topics cursors. Some passages describe the MCP Apps view UI and a downstream create flow rather than this call's behavior, which slightly muddies rather than contradicts the read-only profile.

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

Conciseness2/5

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

The routing instruction is correctly front-loaded in the first two sentences, but the remainder is a dense run-on that mixes invocation guidance with host-rendering trivia (Steeping area placement, view height, paginator, tag pills) that does not help an agent decide or call. For a 7-parameter tool this much unrelated UI detail dilutes the actionable content and invites misreading of what this call actually returns.

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 a tool with 7 parameters and no output schema, the description covers what comes back (every editable Topic, ranked, with weaker options unchecked), how paging works across pages, and what happens when nothing matches (the 'Start a new topic for this chat' path gated on explicit user choice and confirmation). Nothing an agent needs in order to invoke it correctly appears to be 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?

With only 14% schema description coverage (only `autocomplete` is documented), the description does real compensating work: it names title, summary and links as the send payload, explains chat_url as an optional conversation URL whose value is excluded from matching/public linking, gives the codex://threads/<id> value convention and a warning never to invent an ID, and clarifies cursor/'optional name query' reuse with nextCursor. The mapping is stated in prose rather than tied to parameter names in a few places, so it is strong but not airtight.

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?

The description states a specific action (surface candidate Topics for the user to pick) and a precise trigger scope: the user wants to send/save/share something without naming a Topic. It explicitly separates itself from send_to_topic ('A named Topic goes straight to send_to_topic') and from the create_topic/suggest_sources flow for new topics, so an agent can route correctly 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 when-to-call (unnamed destination, phrases like 'send this to Carl'), when-not-to-call ('Never call it on your own initiative'), the ordering constraint ('call this before send_to_topic and wait for their choice'), and named alternatives for the other two paths (send_to_topic for a named Topic, create_topic/suggest_sources for a new Topic). This is close to a complete decision tree.

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.