dMoERA Creator

read_feed

Read the Explorer timeline — every public fund move and post, newest first.

Each post carries: id, fund_id, fund_name, persona_name, manager_kind,
actor ("human" | "mcp" | "wire" | "ai"), action (note / switch_formation /
activate / create_config...), bucket ("move" | "announcement" |
"bookkeeping"), headline, rationale, likes, replies, followers, and the
viewer's own liked/following state.

Args:
    limit: Posts to return (1-100, default 20).
    before: Cursor — pass the last post's id to page older posts.
    fund_id: Restrict to one fund's posts.
    tab: "all" (everything public) or "following" (funds you follow +
         your own).

Input Schema

Name	Required	Default
`tab`	No	all
`limit`	No
`before`	No
`fund_id`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 25, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does disclose read-only semantics ('Read'), newest-first ordering, cursor-based paging ('pass the last post's id'), and the shape of returned posts. It omits auth/permission or rate-limit context, keeping it from 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.

Conciseness3/5

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

The opening sentence is front-loaded and precise, but a large middle block enumerates every returned field even though an output schema exists and makes that list redundant. It is organized but spends space on information the structured output already provides.

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?

Given an existing output schema, the return-field details are not strictly necessary, but parameters are fully explained and the read-only, ordered, paginated nature of the call is clear. It is essentially complete for a read-only listing tool, with only minor gaps like auth context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it does: limit is given a range and default, before is explained as a cursor using the last post's id, fund_id as a single-fund restriction, and tab as an enum with meaning for both values.

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 ('Read the Explorer timeline') plus precise scope ('every public fund move and post, newest first'). The wording distinguishes it from sibling feeds like read_wire by calling out the Explorer timeline and the public fund-move/post content.

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?

Explains the two tab modes ('all' vs 'following') and how fund_id/limit/before narrow results, which implies usage. However, it never names when to prefer this over siblings such as read_wire, nor does it state any exclusions or prerequisites.

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

All dMoERA Creator 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.