Skip to main content
Glama

Search sessions by speaker

wwdc_speaker_search
Read-onlyIdempotent

Find WWDC sessions featuring a specific speaker by name or partial name, optionally filtered by year. Use it to locate talks, transcripts, and related sessions for a given presenter.

Instructions

Find all WWDC sessions featuring a speaker. Case-insensitive substring match against the speakers field.

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": {
      "speaker": "<speaker>"
    },
    "name": "wwdc_speaker_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearNoRestrict to a specific WWDC year.
limitNo
formatNoResponse formatmarkdown
speakerYesSpeaker name (or partial name), e.g. 'Tim Cook', 'Quinn'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.2.3
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / speaker / maxLength
      Added value: +500
    • addedInput schema / properties / speaker / minLength
      Added value: +1
    • addedInput schema / properties / year / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / year / minimum
      Added value: +-9007199254740991
  2. First observedv0.2.1

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed world, so the safety profile needs no restatement. The description adds genuinely useful behavior beyond that: the speaker field is matched by case-insensitive substring, meaning 'Quinn' will catch multi-speaker entries. It says nothing about result ordering, whether the year filter narrows before or after matching, or truncation at the limit.

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 sentences, no filler, and the core scope is stated before the matching caveat. Every clause carries information an agent would otherwise have to guess.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a four-parameter search tool with rich annotations this covers the essentials, and with no output schema the agent still has no idea what a result looks like or how limit interacts with truncation. The year filter is documented in the schema but the description never confirms that year narrows the search alongside the speaker match.

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 75%, and the description usefully sharpens the required 'speaker' parameter into a case-insensitive substring rather than an exact-name match, which is a real semantic commitment the schema only hints at with 'partial name'. The remaining parameter (limit, default 20 / max 50) gets no elaboration, but its bounds are self-documenting in the schema.

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?

The description gives a specific verb and resource ('Find all WWDC sessions featuring a speaker') plus the matching rule ('Case-insensitive substring match against the speakers field'), which separates it in spirit from topic- or keyword-oriented siblings like wwdc_search and wwdc_list_sessions. It stops short of naming any sibling as the alternative path, so an agent must infer that distinction from the resource wording alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied: call this when you know a person's name rather than a topic or session code, and the substring note signals that partial names work. There is no explicit when-not guidance and no mention of what to use instead for topic, keyword, or full-text lookups (wwdc_search, wwdc_transcript_search), which would be the natural steering for an agent among 40+ siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.