context-saver-mcp

Lazy-load downstream tools

cs_load

Load specific downstream tools into the current session to return their input schemas and make them directly callable, using exact IDs, glob patterns, or bare names.

Instructions

Load specific downstream tools into this session: their full input schemas are returned here and the tools become directly callable (the client also receives tools/list_changed). Accepts exact ids ("server__tool"), globs ("github:*") or bare tool names.

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": {
      "tools": "<tools>"
    },
    "name": "cs_load"
  }
}

Input Schema

Name	Required	Description	Default
`tools`	Yes	Tool ids or glob patterns to load

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.2Nov 11, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations, the description carries the full load and does disclose real behavioral effects beyond a plain read: session state is mutated, the tools become directly callable, the client receives a tools/list_changed notification, and the call returns full schemas. Gaps remain around idempotency of repeated loads, error behavior for unknown ids, and whether unloading is required to free the session.

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?

A single dense sentence, front-loaded with the verb and effect, with parenthetical examples that each earn their place. It is slightly compressed and would read faster split into effect and accepted-formats clauses, but there is no filler.

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?

The tool is simple (one required array param) and has no output schema, so the description must cover the return value itself - which it does by stating that full input schemas are returned. Only error and ambiguity handling (e.g. a bare name matching across servers) is left unaddressed.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning the schema lacks: the accepted forms are exact ids in the "server__tool" shape, globs like "github:*", and bare tool names. That is actionable syntax detail not present in the one-line schema property description.

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 a specific verb and resource (load downstream tools into this session) and states the observable result: full input schemas returned, tools become directly callable, and a tools/list_changed notification fires. It is clearly distinct in effect from cs_call or cs_unload, though it never names a sibling explicitly.

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?

Usage is implied by the word "load" and by "lazy-load" in the title, but there is no explicit when-to-use statement, no prerequisite (e.g. discover first), and no exclusions such as when to use cs_call instead of loading. An agent must infer the routing from sibling names.

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

Deploy Server