Skip to main content
Glama

search_posts

Read-only

Find published posts by what they say: "find my post about our dog", "did I ever write about pricing?", "Alex's posts mentioning the launch". Searches every post on this workspace's channels, including history imported from LinkedIn and posts made outside DemandBird. Every word in query has to appear in the post (case-insensitive, up to 5 words), so use a few distinctive words, not a sentence; words past the 5th are ignored. No dates means all time. Returns the newest matches first, each with its post_id, date, a snippet, its headline numbers and a link, and says how many matched in all. There are no further pages: when there are more matches than limit, narrow with dates, platform or more words. No match says so. The post_id works with get_post_analytics and tag_published_post. To browse without words, use list_recent_posts or list_posts_with_metrics; for the best performers, list_top_posts.

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": {
      "query": "<query>"
    },
    "name": "search_posts"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many matches to show (default 10, max 25).
queryYesThe words to look for, e.g. "dog" or "pricing page". Every word must match.
authorNoWhose posts to search. "me" for the person asking ("my post about..."), or a teammate's name ("Alex"). Omit for the whole workspace, which is what "our" / "the team" means.
end_dateNoOptional. Only posts on or before this day, YYYY-MM-DD, inclusive. Omit for up to today.
platformNoOptional. Omit to search every platform.
workspaceNoOptional: the workspace (client) to answer from for this call only, by name (e.g. 'Acme') or numeric id, as returned by list_workspaces. Leave it out to use the current workspace. It does not change the current workspace; use select_workspace for that.
start_dateNoOptional. Only posts on or after this day, YYYY-MM-DD, in the user's timezone. Omit for all time.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / workspace
      Added value: +{
      +  "description": "Optional: the workspace (client) to answer from for this call only, by name (e.g. 'Acme') or numeric id, as returned by list_workspaces. Leave it out to use the current workspace. It does not change the current workspace; use select_workspace for that.",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare a read-only, closed-world read; the description goes well beyond by disclosing the matching rule (every word must appear, case-insensitive, 5-word cap with extras ignored), default all-time coverage when no dates are given, newest-first ordering, the fields returned, a total match count, and the absence of pagination. It also covers the negative case ("no match says so"), which an agent needs to avoid retrying pointlessly.

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 intent examples before the mechanical rules, and almost every sentence carries decision-relevant information. There is mild duplication with the schema ("No dates means all time" vs. the start_date description; the every-word rule appears in both query description and prose), which keeps it out of the top score.

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?

For a 7-parameter read tool with no output schema, the description supplies the return shape, ordering, total count, and paging behavior — everything an agent needs to call it, interpret results, and decide whether to retry or reformulate. Nothing material is missing.

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 already 100%, so the baseline is 3; the description adds real meaning on top by explaining that `limit` is a hard ceiling with no paging and how to compensate, and by tying `query`'s word-matching rule to the 5-word cutoff. It largely restates the author/date/platform semantics the schema already documents, so it stops short of 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 (find published posts by their text) and immediately grounds it in three natural-language user phrasings, so the agent can map an utterance like "did I ever write about pricing?" onto this tool. Scope is made explicit: every post on the workspace's channels, including LinkedIn-imported history and non-DemandBird posts.

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 routes away from siblings: browse without words → list_recent_posts or list_posts_with_metrics; best performers → list_top_posts. It also names the downstream tools the returned post_id feeds (get_post_analytics, tag_published_post) and prescribes the remedy when results overflow the limit (narrow by dates, platform, or more words).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources