postmoderno

Save writing context

set_context

DestructiveIdempotent

Save or rewrite one context document (kind: voice, audience, guardrails, facts, strategy, or learnings). The body replaces the saved one whole. It is stored in Postmoderno, so it survives switching to a different AI client. For when the user says how they want to sound or to post, corrects how a post reads, or shares what worked.

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": {
      "kind": "<kind>",
      "key": "<key>",
      "body": "<body>"
    },
    "name": "set_context"
  }
}

Input Schema

Name	Required	Description
`key`	Yes	Short slug naming this document, e.g. default. Lowercase letters, digits, dash, underscore.
`body`	Yes	The document itself, in markdown. Write it for another writer to follow.
`kind`	Yes	One of: voice (how the user writes), audience (who they write for), guardrails (what to avoid), facts (product/company details worth getting right), strategy (how often and when they post, and which kinds of post go when), learnings (dated notes on what worked and what did not).
`label`	No	Human-readable name for this document.

Output Schema

Name	Required	Description	Default
`key`	Yes
`kind`	Yes
`note`	No
`scope`	Yes
`created`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 8, 2026

changedInput schema / properties / kind / description

Previous value: -"One of: voice (how the user writes), audience (who they write for), guardrails (what to avoid), facts (product/company details worth getting right)."New value: +"One of: voice (how the user writes), audience (who they write for), guardrails (what to avoid), facts (product/company details worth getting right), strategy (how often and when they post, and which kinds of post go when), learnings (dated notes on what worked and what did not)."

First observedNov 7, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare destructive=true and idempotent=true, and the description earns credit by explaining exactly what is destroyed: "The body replaces the saved one whole," i.e. a full overwrite rather than a merge, which also explains the idempotent behavior. It further adds persistence context ("stored in Postmoderno, so it survives switching to a different AI client") that no annotation conveys. It does not say what happens to the optional label when omitted, keeping it below 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.

Conciseness4/5

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

Three sentences, front-loaded with the verb and resource, then the replacement semantics, then the persistence fact and trigger conditions. The inline re-listing of all six kinds duplicates the schema's enum and is the one mildly wasteful element.

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 destructive mutation tool, the description covers the essential risks (full-body replacement, persistence scope) and the trigger situations, and an output schema exists so return values need no explanation. The only gap is the absence of explicit routing to sibling tools like get_context or delete_context.

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%, including an enumeration of the kind values that the description merely repeats. The description adds one genuinely useful nuance — that body is a whole-document replacement — but gives no guidance on key reuse semantics or label behavior. Baseline 3 is appropriate when the schema carries the parameter detail.

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?

States a specific verb+resource ("Save or rewrite one context document") and enumerates the six kinds it applies to, so an agent can tell it apart from get_context and delete_context by the mutation verb alone. It stops short of explicitly naming those siblings as alternatives, so the differentiation is implied 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 Guidelines4/5

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

The final sentence gives concrete trigger conditions: the user states how they want to sound or to post, corrects how a post reads, or shares what worked. That is a clear when-to-use context, but there is no when-not guidance and no instruction to check existing context with get_context first.

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

All postmoderno tools Inspect

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

Need Help?