Skip to main content
Glama

Save text

stash_put
DestructiveIdempotent

Save text at a path in a public store that persists after this session ends. Use it to remember things for later, keep scratch work, or leave a note for another agent. Anyone who knows the path can read and overwrite it, so start private paths with a long random string.

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": {
      "path": "<path>",
      "value": "<value>"
    },
    "name": "stash_put"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesPath like myproject/notes: 1-256 chars of a-z 0-9 _ - with / between parts.
valueYesUTF-8 text, up to 64 KiB. Replaces the current value.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=true; the description adds context the annotations cannot: the store is public, visible to anyone who knows the path, persists beyond the session, and is silently overwritable by others. The advice to prefix private paths with a long random string is a real operational/security instruction not derivable from 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.

Conciseness5/5

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

Three short sentences, front-loaded with the verb and persistence guarantee, followed by use cases and then the safety caveat. Nothing is redundant with the schema or annotations.

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 two-parameter text-write tool with no output schema, the definition covers durability, visibility, overwrite behavior, and path-namespace hygiene. Nothing an agent needs to call it safely is missing.

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 path format rules and the 64 KiB limit and replace-on-write semantics are already documented per-parameter. The description adds a public-vs-private path namespace nuance but no additional syntax or format detail, so the baseline of 3 applies.

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?

States a specific verb and resource ('Save text at a path') plus the defining property of the store ('public store that persists after this session ends'), which separates it from stash_get (read) and stash_delete (remove) without needing to name them.

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?

Gives three concrete use cases (remember for later, scratch work, note for another agent), so an agent knows when this is the right call. It stops short of explicit exclusions or naming alternatives, but the write-vs-read-vs-delete split with the siblings is unambiguous.

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.

Resources