Skip to main content
Glama
Sign In

Liminal

by ai.physea
OverviewDiscussionsAdmin

fetch

Read-onlyIdempotent

Full saved answer text by exact search id; caller-owned only.

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": {
      "id": "<id>",
      "context": "<context>"
    },
    "name": "fetch"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
contextYesUser's goal in one short sentence; no personal data or secrets.
llm_modelNoYour exact model id for analytics, or "unknown"; never guess.

Output Schema

NameRequiredDescriptionDefault
idYes
urlYes
textYes
titleYes
metadataYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / required
      Previous value: -[
-  "id",
-  "context",
-  "llm_model"
-]New value: +[
+  "id",
+  "context"
+]
  2. Changed2 schema fields changed
    • changedInput schema / properties / context / description
      Previous value: -"Describe the user's goal in one short sentence. Omit personal data and secrets."New value: +"User's goal in one short sentence; no personal data or secrets."
    • changedInput schema / properties / llm_model / description
      Previous value: -"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."New value: +"Your exact model id for analytics, or \"unknown\"; never guess."
  3. Added

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description contributes one genuinely new behavioral fact, the 'caller-owned only' access boundary, but says nothing about what happens on a miss or unauthorized id. Comparable to the calibration case where a scoping constraint earned a 3.

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?

One sentence, front-loaded with the return payload and the keying parameter, with no filler. It is efficient, though the semicolon-clause style is compressed to the point of being telegraphic.

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 simple idempotent read with an output schema and full annotation coverage, the description plus schema is nearly sufficient: the agent knows the payload, the key, and the ownership restriction. Only failure behavior for an unknown or non-owned id is left unstated.

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 67%, and the schema already documents 'context' (one-sentence goal) and 'llm_model' (exact model id or "unknown"). The description adds only the 'exact' qualifier on id, which does clarify that a fuzzy or approximate id will not resolve, but leaves the other two parameters 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?

Names a specific verb+resource: return the full saved answer text keyed by an exact search id. The phrase 'exact search id' implicitly separates it from the sibling 'search' (which produces ids) and from 'read', but it never names an alternative, so differentiation is inferred rather than stated.

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?

Implies usage — call it when you already hold an exact search id — and restricts scope to caller-owned answers. There is no explicit when-not condition, no statement of what to do if the id is stale or belongs to another caller, and no named alternative for full-text retrieval.

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

All Liminal 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