Skip to main content
Glama
WebCake Storefront MCP

WebCake Storefront MCP

by vuluu2k

cached_result

Read-only

List and page through large server-side results, then read a specific slice by cache ID to inspect oversized tool output without loading it all.

Instructions

Large results kept server-side: list and page through them. Pick the operation with action and pass that action's arguments (help:true returns its full documentation and schema).

  • list_cached_results: List the large results currently held in the session cache (id, label, size, age).

  • read_cached_result: Read a slice of a large cached result produced by another tool (look for "cached":true + a cache_id in its output).

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": {
      "action": "<action>"
    },
    "name": "cached_result"
  }
}

Input Schema

NameRequiredDescriptionDefault
helpNoReturn the action's full documentation and argument schema instead of running it
actionYesWhich operation to run
lengthNoNumber of characters to return (default 12000) [read_cached_result]
offsetNoStart character offset (default 0) [read_cached_result]
cache_idNoThe cache_id returned by the producing tool (e.g. [read_cached_result]

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.8.0

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, so safety is covered by structured data. The description adds genuinely useful behavior context beyond that: results live in a session-scoped cache rather than being returned inline, reads are slice-based via offset/length, and list returns id, label, size, and age. It does not say what happens when a cache entry expires or is missing, which is the main behavioral gap.

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?

Front-loaded framing sentence, then a compact action-dispatched list with the shared `help:true` convention noted up front. Every line carries information and there is no boilerplate or repetition of schema content.

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 5-parameter dispatcher with no output schema, the definition covers purpose, action selection, the help mechanism, and the trigger for the read path, and even sketches the fields list returns. The remaining gap is failure/expiry behavior for stale cache_ids, which an agent would need to handle a miss.

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 3 is the baseline. The description goes slightly beyond it by framing offset/length as 'a slice' of a specific cached result and by explaining the provenance of `cache_id` (emitted by the producing tool's output), which is meaning the schema does not spell out. Defaults for length and offset are left to the schema.

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 states a concrete resource (large results held server-side in the session cache) and the two concrete operations available under `action` (list_cached_results, read_cached_result). An agent can tell what the tool is for without opening the schema. It does not differentiate itself from any sibling, and no other sibling appears to handle caching, but the definition itself provides no explicit contrast.

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?

Guidance is concrete on the entry trigger: read_cached_result is for results produced by another tool, identified by a `"cached":true` marker plus a cache_id in that tool's output. It also explains the help:true escape hatch for retrieving per-action documentation. There is no explicit when-not statement or suggestion of a non-cached alternative for smaller results.

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