Skip to main content
Glama
Sign In

Collide MCP

by com.collidemcp.api
OverviewDiscussionsAdmin

recap

Read-only

What each agent did in this repo, session by session: edits, lines, tokens, model, estimated cost, rationales and top paths. Use it to answer "what happened" or "what did this cost". Read-only. Returns one entry per session and a dashboard link.

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": "recap"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoHow many days back, up to 90 (default 1).
repo_idNoThe repository id, e.g. github.com/org/repo (the Cork briefing names it). Omit it to use the repo your session works in.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / repo_id / description
      Previous value: -"The repository id, e.g. github.com/org/repo (the Collide briefing names it). Omit it to use the repo your session works in."New value: +"The repository id, e.g. github.com/org/repo (the Cork briefing names it). Omit it to use the repo your session works in."
  2. Changed2 schema fields changed
    • changedInput schema / properties / repo_id / description
      Previous value: -"The repository id, e.g. github.com/org/repo (repo_id in .collide/config.json)."New value: +"The repository id, e.g. github.com/org/repo (the Collide briefing names it). Omit it to use the repo your session works in."
    • changedInput schema / required
      Previous value: -[
-  "repo_id"
-]New value: +[]
  3. Changed2 schema fields changed
    • addedInput schema / properties / days / description
      Added value: +"How many days back, up to 90 (default 1)."
    • addedInput schema / properties / repo_id / description
      Added value: +"The repository id, e.g. github.com/org/repo (repo_id in .collide/config.json)."
  4. Changed6 schema fields changed
    • removedInput schema / properties / days / default
      Removed value: -1
    • removedInput schema / properties / days / description
      Removed value: -"How many days of history to include."
    • removedInput schema / properties / days / title
      Removed value: -"Days"
    • removedInput schema / properties / repo_id / description
      Removed value: -"Repository id — the git remote (e.g. github.com/acme/api) or a bare folder name; a #branch suffix scopes to that branch."
    • removedInput schema / properties / repo_id / title
      Removed value: -"Repo Id"
    • removedInput schema / title
      Removed value: -"recapArguments"
  5. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/ non-destructive, so the 'Read-only' sentence adds nothing, but the description earns credit elsewhere: it states the return shape (one entry per session), what metrics each entry carries, and that a dashboard link comes back. That tells the agent the response is per-session aggregated summary data, not raw events — information not available in any structured field.

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

Conciseness4/5

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

The payload — what the tool reports — is front-loaded in the first sentence, followed by usage triggers and return shape. It is dense and earns nearly every clause; the only dead weight is the 'Read-only' sentence, which merely restates the annotation.

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?

With only two optional parameters, no output schema, and simple annotations, the description covers what the agent needs: the aggregation unit (per session), the fields returned, the dashboard link, and when to reach for it. Nothing about authentication, pagination, or empty-result behavior is stated, but for a small read-only summary tool that is a minor gap.

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 both parameters (days, repo_id) are already fully documented in the schema, including the 90-day cap and the repo_id format. The description only implicitly echoes repo scoping via 'in this repo' and says nothing about the time window, so the baseline 3 applies with no added meaning.

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 the resource and its granularity precisely: per-session agent activity in a repo, with an explicit content list (edits, lines, tokens, model, cost, rationales, top paths). This separates it from memory-style siblings like recall or remember without needing their schemas. It is not a clean verb+resource phrase, but the scope is unmistakable.

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 gives concrete triggering questions — 'what happened' and 'what did this cost' — which directly maps to an agent's intent. It stops short of naming exclusions or a sibling to prefer for adjacent questions (e.g. single-code-location lookups), so it is clear context rather than full routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Collide MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources