Skip to main content
Glama

Search what AI leaders said

search_moments
Read-onlyIdempotent

Search the moments Real Alpha cut from long interviews with the people building AI. Use it when someone asks what AI founders, CEOs or researchers have said about a subject, or wants sources, quotes or expert views on an AI question. Matches the words of query against what each moment is about, the speaker's quote and its takeaways, best match first. Filter by who is talking (person), a company (someone from it talking, or it being discussed), a show, or how recent. Each result has the speaker, what they do, the show, the date, their quote, and the moment's page to cite. It only covers the episodes Real Alpha has cut, so no match doesn't mean nobody said it.

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_moments"
  }
}

Input Schema

NameRequiredDescriptionDefault
showNoOnly moments from this show: "Lenny's Podcast", "Dwarkesh Podcast", "No Priors"
limitNoHow many moments to return, 8 if not given, 20 at most
queryYesWhat to look for, in a few words: "AI bubble", "coding agents replacing engineers", "scaling laws"
sinceNoOnly episodes out on or after this date, YYYY-MM-DD
personNoOnly moments where this person is talking, by name: "Sam Altman", "Dario Amodei"
companyNoOnly moments from someone at this company, or about it: "Anthropic", "Nvidia"

Output Schema

NameRequiredDescriptionDefault
tipNoWhat to try when nothing matched
matchesYesHow many moments matched, of which `moments` has the best
momentsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "https://json-schema.org/draft/2020-12/schema",
      +  "additionalProperties": false,
      +  "properties": {
      +    "matches": {
      +      "description": "How many moments matched, of which `moments` has the best",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "moments": {
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "cite": {
      +            "description": "A line to credit it by",
      +            "type": "string"
      +          },
      +          "date": {
      +            "description": "When the episode came out, YYYY-MM-DD",
      +            "type": "string"
      +          },
      +          "episode": {
      +            "type": "string"
      +          },
      +          "episode_url": {
      +            "description": "The episode's page, from the moment on",
      +            "type": "string"
      +          },
      +          "length": {
      +            "type": "string"
      +          },
      +          "quote": {
      +            "description": "Their words, as said in the episode",
      +            "type": "string"
      +          },
      +          "show": {
      +            "type": "string"
      +          },
      +          "show_page": {
      +            "type": "string"
      +          },
      +          "slug": {
      +            "description": "The moment's id, for get_moment",
      +            "type": "string"
      +          },
      +          "speaker": {
      +            "description": "Who's talking",
      +            "type": "string"
      +          },
      +          "speaker_page": {
      +            "description": "Their page on realalpha.app, with every moment of theirs",
      +            "type": "string"
      +          },
      +          "speaker_role": {
      +            "description": "What they do",
      +            "type": "string"
      +          },
      +          "starts_at": {
      +            "description": "Where in the episode it starts, like 31:50",
      +            "type": "string"
      +          },
      +          "summary": {
      +            "type": "string"
      +          },
      +          "title": {
      +            "type": "string"
      +          },
      +          "url": {
      +            "description": "The moment's page, which plays the episode from it: the link to cite",
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "slug",
      +          "title",
      +          "show",
      +          "show_page",
      +          "episode",
      +          "date",
      +          "summary",
      +          "starts_at",
      +          "length",
      +          "url",
      +          "episode_url",
      +          "cite"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "tip": {
      +      "description": "What to try when nothing matched",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "matches",
      +    "moments"
      +  ],
      +  "type": "object"
      +}
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Adds real behavior beyond the annotations: results are ranked best-match-first, matching happens against topic, quote and takeaways, and company filtering covers both the speaker's employer and mere discussion of the company. It also discloses a coverage limitation ('no match doesn't mean nobody said it'), which prevents the agent from over-claiming absence. Read-only/idempotent safety is already covered by annotations, so this sits just short of a 5.

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?

Front-loaded with the core action, then usage triggers, then matching/filter semantics, then result shape, then the coverage caveat – a sensible priority order. Sentences are dense but each adds distinct information; nothing reads as filler.

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?

Given six parameters and an output schema, the description covers purpose, matching logic, filters, ranking, and the important negative-result caveat. Describing the result fields is mildly redundant with the output schema, but the completeness otherwise leaves nothing an agent needs before invoking it.

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 contributes meaning beyond the field docs by explaining what `query` is matched against and clarifying that `company` is a two-way filter (speaker affiliation or topic). `person`, `show`, `since` and `limit` are left to the schema, which already documents them fully.

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 – searching moments cut from long interviews with AI builders – plus the exact matching surface (speaker quote, takeaways, topic). An agent can distinguish this full-text semantic search from listing-type siblings like latest_moments or person-centric ones 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 Guidelines4/5

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

Gives concrete triggering conditions: when someone asks what AI founders/CEOs/researchers said, or wants quotes, sources, or expert views. It does not name an alternative tool or state an explicit when-not condition, and the filter guidance ('if you want a specific person's take...') is only implicit through the `person` parameter.

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.