Skip to main content
Glama

Find Similar Posts

find_similar_posts
Read-onlyIdempotent

[Read · free] Find persisted posts whose embeddings are nearest to a free-text query — pgvector cosine over the local post library, no LinkedIn pull, free. Use when you have a block of text (a draft, a paragraph, a competitor's post) and want similar posts you've already collected. For keyword search prefer search_posts; for fresh LinkedIn keyword pulls use linkedin_post_search. Pass profile_id to scope to a tracked profile, collection_id to scope to a collection, or neither to search the entire library.

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": {
      "text": "<text>"
    },
    "name": "find_similar_posts"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesText to find similar posts for
limitNoMax results to return (1-50, default 5)
profile_idNoOptional tracked profile ID from list_profiles (scopes search to this profile's posts)
collection_idNoOptional post_collections.id (scopes search to this collection's members)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new context: the operation is free and costs no credits, it runs over locally persisted embeddings rather than pulling from LinkedIn, and similarity is embedding-based rather than lexical. It does not say whether results carry similarity scores or how ties/ordering are handled, which is the one remaining behavioral gap.

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?

The core capability and the free/no-LinkedIn-pull qualifier are front-loaded in the first clause, and every subsequent sentence carries routing or scoping information. It is slightly dense — bracketed tags plus em-dash-heavy phrasing — but nothing is redundant.

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 four-parameter read tool with no output schema, the definition covers mechanism, cost, scope selection, and sibling alternatives. The gap is that it never says what a result looks like (ranked posts only? with similarity scores?) nor that an empty library of embeddings yields nothing — minor omissions for a retrieval tool whose output shape is conventional.

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 coverage is 100% — every parameter already has a description, including the 1-50 limit and the origin of profile_id. The description restates the two scoping parameters but adds the meaningful default ('or neither to search the entire library') that the schema leaves implicit. That is a small increment over an already-complete schema, so the baseline 3 holds.

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?

The description gives a specific verb and resource — find persisted posts whose embeddings are nearest a free-text query — and names the retrieval mechanism (pgvector cosine over the local post library). It explicitly distinguishes itself from `search_posts` (keyword) and `linkedin_post_search` (fresh LinkedIn pulls), so an agent can pick it without opening the 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?

It states the triggering condition concretely ('when you have a *block of text* — a draft, a paragraph, a competitor's post') and routes to the two named alternatives with their own conditions. It also spells out the scoping decision tree: profile_id, collection_id, or neither for the whole library.

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