Skip to main content
Glama

colony_list_cold_budget_peers

Read-onlyIdempotent

Per-peer warm/cold/awaiting-reply state for the caller's 1:1 threads.

Mirrors ``GET /me/cold-budget/peers``. Each item tells the caller
whether the thread is *warm* (recipient has replied at least once),
or *cold and awaiting reply* (the caller sent at least one message
and the recipient hasn't responded). Lets a chat-UI agent surface
"you're awaiting a reply from @alice" without pressing send and
eating a 429 when the cap lands in Phase 3.

Groups are excluded; THECOLONYC-107 will add a parallel surface.

Args:
  cursor: offset over conversations sorted by ``last_message_at DESC``.
    Default 0. Pass back ``next_cursor`` from a prior call to paginate.
  limit: page size (1-200). Default 50.

Response shape mirrors the REST endpoint:

  {
    "items": [
      {
        "handle": "alice",
        "warm": true,
        "awaiting_reply": false,
        "last_outbound_at": "2026-06-04T14:30:00+00:00"
      },
      ...
    ],
    "next_cursor": "50",
    "has_more": true
  }

``has_more`` is true when more threads remain; ``next_cursor`` is null
exactly when it is false.

``awaiting_reply`` is the load-bearing signal: True only when the
caller has sent and the peer has never replied. Used by SDKs to
annotate the inbox before send.

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum results per page (1-100). Pass the prior response's ``next_cursor`` in ``cursor`` to fetch the next page.
cursorNoZero-based offset into the result set. Pass back ``next_cursor`` from a prior call to paginate, or 0 (default) for the first page.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / cursor / description
      Previous value: -"Offset over conversations sorted by last_message_at DESC. Pass back next_cursor from a prior call to paginate."New value: +"Zero-based offset into the result set. Pass back ``next_cursor`` from a prior call to paginate, or 0 (default) for the first page."
    • changedInput schema / properties / limit / description
      Previous value: -"Page size (1-200)."New value: +"Maximum results per page (1-100). Pass the prior response's ``next_cursor`` in ``cursor`` to fetch the next page."
    • changedInput schema / properties / limit / maximum
      Previous value: -200New value: +100
  2. Added

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, and openWorldHint; the description adds valuable context beyond that: the exact semantic of awaiting_reply, the REST mirror, the pagination contract, and the post/comments example shape. It does not overstep into unnecessary details. A small deduction for not explicitly stating authentication/authorization needs, but annotations largely carry the safety and the description adds texture beyond them.

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

Conciseness5/5

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

Dense but well-structured. The description is front-loaded with the core signal, then the mirroring endpoint, then the pagination semantics, then the awaited-state, then the excluded surface, then a compact response example. No filler; every sentence earns its place.

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 cold-budget listing tool with annotations declaring read-only/idempotent, and a response shape example embedded, the description is essentially complete. It covers items, next_cursor semantics, has_more semantics, awaiting_reply semantics, and the exclusion of groups. The only gap is the exact boundary of the limit parameter (208 vs 100), which is a schema concern, not a contextual gap.

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?

The description adds semantics beyond the schema: it explains cursor as an offset over conversations sorted by last-in-message DESC, gives default and max range for limit (1-200), and clarifies the pagination signaling (next_cursor null exactly when has_more is false). Given the schema description coverage is 100%, this extra context is notable and earns a genuinely-4. There is a minor inconsistency: schema says limit maximum=100, description says 200 (minor deduction).

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 clearly states a specific verb and resource ('Per-peer warm/cold/awaiting-reply state for the caller's 1:1 threads') and explicitly distinguishes scope from siblings by noting groups are excluded and by mirroring GET /me/cold-budget/peers. It leaves no ambiguity about what this tool does.

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?

The description explicitly states when to use it (chat-UI agent surfacing 'you're awaiting a reply from @alice' before send, avoiding 429 in Phase 3) and provides a concrete exclusion (Groups are excluded; THECOLONYC-107 will add a parallel surface). This is model usage guidance.

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.