Skip to main content
Glama

cachly — Explain it once. Every AI knows it.

session_end

Save a session summary when you finish working. Records what was accomplished, files changed, and lesson count. The next session_start will show this summary as "Last session". Call this when ending a work session, before going idle, or before summarizing. Ambient Learning: if workspace_path is provided, reads git log since session start and auto-learns from commits.

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": {
      "summary": "<summary>"
    },
    "name": "session_end"
  }
}

Input Schema

NameRequiredDescriptionDefault
summaryYesBrief summary of what was accomplished this session (2-3 sentences)
instance_idNoUUID of the cache instance.
files_changedNoKey files changed this session (optional)
workspace_pathNoAbsolute path to the project root (e.g. "/Users/you/myproject"). Enables Ambient Learning — reads git log since session start and auto-learns from commit messages.
lessons_learnedNoNumber of new lessons stored this session (optional)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and mostly does: it discloses that the call persists data into a store that session_start later reads back, and that supplying workspace_path triggers an additional side effect — reading git log since session start and auto-learning from commit messages. That is genuine behavioral disclosure beyond the schema. It does not cover failure modes (non-git workspace, missing session start), which keeps it from a 5.

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 trigger list ("when ending a work session, before going idle, or before summarizing") largely repeats the opening sentence's framing, and the ambient-learning clause duplicates the workspace_path schema text. It is front-loaded and readable, but two of four sentences carry redundant weight.

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 five-parameter write tool with no annotations and no output schema, the description does the important work: it explains what is stored and how it is later surfaced, so an agent understands the downstream payoff. It is nearly complete, with the only real hole being how this differs from session_handoff and what happens when no prior session_start exists.

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 description coverage is 100%, so the schema already documents all five parameters, including the ambient-learning note on workspace_path. The description adds little parameter-level meaning beyond restating the summary contents and the git-log behavior that the schema already states. Baseline 3 is appropriate.

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 uses a specific verb and resource ("Save a session summary") and enumerates the payload: accomplishments, files changed, lesson count. It also tells the agent where the data surfaces later ("the next session_start will show this summary as 'Last session'"), which makes the effect concrete. It never distinguishes itself from the sibling session_handoff, which plausibly occupies the same end-of-session niche, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives trigger conditions: "when ending a work session, before going idle, or before summarizing." That is real when-to-use guidance, but there are no exclusions and no routing to alternatives — notably session_handoff, which is named as a sibling and could easily be confused with this tool. "Before summarizing" is also vague enough to be ambiguous about ordering.

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.