Skip to main content
Glama

Search Development Radio episodes

search_episodes
Read-only

Keyword search over Development Radio episodes: titles, topics, chapter titles, takeaways, summaries, cited source titles and the full timed transcripts. Up to six keywords of three or more characters are used; a keyword matches at the start of a word. Episodes are ranked by how many keywords they contain, and when any episode contains more than half of them, episodes containing half or fewer are left out. Each result comes with its id, title, date, page URL, the best-matching passage (with a timestamp when it comes from the transcript) and the URLs of the primary sources the episode cites. Use this when you need a sourced account of a security incident, CVE, outage, AI or software-development news item, or an engineering practice such as lock expiry, replica lag, queue fairness or content security policy. The show's hosts are AI-generated voices.

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_episodes"
  }
}

Input Schema

NameRequiredDescriptionDefault
laneNoOnly episodes in this lane of the show.
limitNoMaximum number of episodes to return.
queryYesKeywords, for example "nginx http2 rce" or "redis lock expiry".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond readOnlyHint/openWorldHint, it discloses the ranking rule, the keyword count and minimum-length constraint, prefix-word matching, and a non-obvious truncation rule ('when any episode contains more than half of them, episodes containing half or fewer are left out') that an agent must know to interpret an empty or short result. It also pre-empts a trust issue by noting the hosts are AI-generated voices.

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 scope, then matching mechanics, then use cases, then the AI-voice caveat — a sensible order with little filler. The closing sentence about AI-generated hosts is the one line that could be trimmed, though it does carry source-reliability meaning.

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-value burden itself and does so by naming the id, title, date, page URL, best-matching passage with optional timestamp, and cited source URLs. Combined with the ranking and filtering rules, an agent has everything needed to call it and interpret results 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; the description earns above that by adding matching semantics the schema cannot express — up to six keywords, minimum three characters, prefix-at-word-start matching. The lane and limit parameters are left entirely to the schema, so it does not fully compensate for behavioral nuance there.

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 opens with a precise verb+resource pair ('Keyword search over Development Radio episodes') and then enumerates the exact fields searched, which cleanly separates it from listing, fetching, or transcribing episodes. An agent can tell this is the only free-text retrieval path among the siblings without inspecting 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 Guidelines4/5

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

It gives concrete triggering scenarios ('a sourced account of a security incident, CVE, outage, AI or software-development news item, or an engineering practice such as lock expiry, replica lag...'), which is far stronger than generic guidance. It stops short of naming the sibling tools or stating when *not* to use it (e.g. 'use get_episode for a known episode id').

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.