Skip to main content
Glama

list_top_posts

Read-only

Posts ranked best to worst by a metric. Rank recent posts to answer "what's my best post?", "what was Alex's best post?", "what was our top post this month?", "worst post?". WHOSE POSTS: this workspace may have several people posting, so pass author whenever the question names one. "my"/"mine"/"I" -> author: "me". A person's name -> that name, e.g. author: "Alex". "our"/"the team"/"we", or no one named at all -> omit author for the whole workspace. Do not assume "my" means the workspace. Omit platform to rank across every connected network; pass one to focus. Defaults to ranking by engagement rate. Use order: bottom for worst-performers. Returns each post's id, stats, snippet, and link.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_top_posts"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many posts (default 5, max 20).
orderNotop (best) or bottom (worst). Default top.
authorNoWhose posts to rank. "me" for the person asking (use this for "my best post"), or a teammate's name for theirs ("Alex"). Omit for the whole workspace, which is the default and is what "our" / "the team" means.
metricNoWhat to rank by. Default engagement_rate. discussion_rate is comments per 1,000 impressions. LinkedIn also tracks profile_views (profile viewers the post drove), members_reached, saves, sends, follows, lift, clicks and premium_cta_clicks (clicks on a Premium member's profile button that came from the post); other platforms track their own subset. A metric a platform doesn't report is refused with the list it does.
periodNoRolling window ending today. Default 30d. For any other window, pass start_date/end_date instead.
end_dateNoOptional. Last day of a custom range, YYYY-MM-DD, inclusive. Defaults to today. Needs start_date.
platformNoOptional. Omit to rank across all platforms.
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. First day of a custom range, YYYY-MM-DD, in the user's timezone. Use for windows the presets don't cover: "last 14 days", "in March", "since Jan 1", "last year". Overrides `period`. Ranges can cover up to 366 days.

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

A4.3/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds genuinely new behavior: the default metric is engagement_rate, per-platform metric subsets exist, and an unsupported metric is 'refused with the list it does' report — a real error behavior an agent must anticipate. It also discloses what comes back (id, stats, snippet, link), which matters because there is no output schema.

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 behavior, then organized into labeled concerns (WHOSE POSTS, platform, ordering, return values), which reads well for an agent. It is dense but a few clauses duplicate schema descriptions verbatim, notably the author and workspace explanations, so there is some redundancy.

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 9 optional parameters, 4 enums, and no output schema, the description covers everything an agent needs: whose posts, which metric, which window, which platform, ordering direction, and the shape of the response. Defaults and error behavior are both stated, so no inference is required to call it correctly.

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 the baseline is 3, but the description still adds selection logic the schema states only tersely: the my/our/name mapping for author, the cross-platform default for platform, and the period-vs-start_date/end_date precedence ('Overrides `period`', 366-day cap). Most of this restates schema text, which caps it below 5.

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?

Opens with a specific verb and resource plus the ranking dimension: 'Posts ranked best to worst by a metric,' followed by concrete question patterns it answers. It is clearly distinct from chronological siblings like list_recent_posts, but it never explicitly separates itself from list_posts_with_metrics or get_post_analytics, which an agent could plausibly confuse it with.

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?

Strong disambiguation guidance on the trickiest choice: 'my'/'mine'/'I' maps to author: 'me', a person's name maps to that name, and 'our'/'the team'/nothing maps to omitting author, with an explicit warning not to treat 'my' as the workspace. It also says to omit platform to rank across all networks and to use order: bottom for worst performers. It stops short of naming sibling alternatives (search_posts, list_posts_with_metrics) and when to prefer those.

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