Skip to main content
Glama

Fmind Freelance AI Architect Website

Search articles

search_articles
Read-only

Search the hosted articles by relevance (BM25 over titles, tags, descriptions, and full text) and return the best matches. Use it to answer what Fmind has written about a topic instead of listing every publication.

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_articles"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagNooptionally keep only articles with this tag, case-insensitive: Agent, Coding, LLM, RAG, MLOps, Cloud, Python, Project, Demo, Guide
limitNomaximum number of results to return (default 10, maximum 50)
queryYeswords to search for across article titles, tags, descriptions, and full text (at most 128 characters)

Output Schema

NameRequiredDescriptionDefault
queryYes
totalYes
articlesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / tag / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "maxLength": 64,
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  2. Changed5 schema fields changed
    • addedInput schema / properties / limit / maximum
      Added value: +50
    • changedInput schema / properties / query / description
      Previous value: -"words to search for across article titles, tags, descriptions, and full text"New value: +"words to search for across article titles, tags, descriptions, and full text (at most 128 characters)"
    • addedInput schema / properties / query / maxLength
      Added value: +128
    • removedOutput schema / $defs / ArticleSummary / properties / canonical
      Removed value: -{
      -  "default": "",
      -  "title": "Canonical",
      -  "type": "string"
      -}
    • removedOutput schema / $defs / ArticleSummary / properties / syndicated
      Removed value: -{
      -  "default": "",
      -  "title": "Syndicated",
      -  "type": "string"
      -}
  3. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  4. Changed1 schema field changed
    • addedInput schema / properties / limit / minimum
      Added value: +1
  5. Changed1 schema field changed
    • addedInput schema / properties / tag
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "optionally keep only articles with this tag, case-insensitive: Agent, Coding, LLM, RAG, MLOps, Cloud, Python, Project, Demo, Guide",
      +  "title": "Tag"
      +}
  6. Changed1 schema field changed
    • changedInput schema / properties / limit / default
      Previous value: -0New value: +10
  7. 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=true and openWorldHint=false, so safety is covered. The description adds real value beyond that by disclosing the relevance model (BM25) and the corpus it scores over, which tells the agent results are ranked rather than exhaustive. It does not discuss result count defaults or ranking ties, but the schema covers limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

Two compact sentences with no filler: purpose and mechanics first, then routing guidance. Every clause carries information an agent can act on.

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 an output schema present, return-value explanation is unnecessary, and the annotations already carry the read-only profile. The description plus the fully covered schema gives an agent everything needed to select and invoke this tool correctly.

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 description coverage is 100%, so query, tag, and limit are already fully documented with lengths, defaults, and the allowed tag list. The description restates that searching spans titles, tags, descriptions, and full text, which mirrors the query parameter description rather than adding new meaning. Baseline 3 applies when the schema does the heavy lifting.

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 names a specific verb and resource ("Search the hosted articles") and goes further by naming the ranking method (BM25) and the fields searched (titles, tags, descriptions, full text). It also distinguishes itself from the listing-style sibling by noting it answers a topic question "instead of listing every publication."

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?

It gives explicit guidance on when to reach for this tool ("to answer what Fmind has written about a topic") and points away from an alternative behavior (listing every publication). It stops short of naming which sibling to use for the excluded case or covering when-not conditions such as fetching a single known article.

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