Skip to main content
Glama
Sign In

SupaBird

by io.supabird.api
OverviewDiscussionsAdmin

filter_posts

Read-onlyIdempotent

Filter posts loaded from an X list or community. Call this after get_list_tweets, get_list_timeline, get_community_tweets, or search_community_tweets when the user wants only posts that match a description.

    Pass the tweets array from that tool response unchanged. Do not drop, summarize, or rewrite posts before filtering.
    description is the user's filter in plain language, for example "posts asking for feedback" or "founders sharing revenue".

    source:
    - "list" — drop replies first, same as Engage lists
    - "community" — keep replies, same as Engage communities
    - omit source when the page is not a list

    Returns only the posts that match, highest engagement first. Display each post's full text, author, and url. Do not paraphrase.

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": {
      "description": "<description>",
      "tweets": "<tweets>"
    },
    "name": "filter_posts"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceNolist drops replies before filtering. community keeps them.
tweetsYesThe tweets array from a list or community load tool. One page, up to 40 posts.
descriptionYesWhat to keep, in the user's words.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false), and the description adds substantial context on top: input must be passed unchanged, replies are dropped for lists but preserved for communities, output is sorted by engagement, and results must be displayed verbatim with text, author, and url. That is behavior an agent could not infer from the structured fields.

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?

Front-loaded with the core action and prerequisite tools, then broken into parameter-scoped lines that are easy to scan. The no-paraphrase instruction is repeated in two places ("Do not drop, summarize, or rewrite" and "Do not paraphrase"), which is slight waste but arguably reinforces a critical constraint.

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?

With no output schema, the description carries the return contract and does so: only matching posts, ordered by engagement, with guidance on how to present them. Input provenance, the reply-handling branch, and the display requirement are all covered for a 3-parameter tool.

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 baseline is 3, but the description earns above that: it constrains tweets to the verbatim array from a prior call (no dropping or rewriting), explains the source enum's reply-handling consequence, and gives example plain-language values for description. Only mild redundancy with the enum's own description keeps it from a 5.

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 ("Filter posts loaded from an X list or community") and immediately bounds the scope to output of four named upstream tools. An agent can distinguish this from the loading tools and from idea-generation siblings without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Explicitly names the four prerequisite tools to call first and the user condition that selects this tool ("when the user wants only posts that match a description"). It also gives an exclusion rule for the source parameter ("omit source when the page is not a list"), which resolves the one ambiguous branch.

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

All SupaBird 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