Summarize Meeting

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

With no annotations, the description carries the full burden and does disclose two real behavioral traits: `send_to_telegram` causes an immediate external push of the formatted summary, and `clean_first` purges Whisper silence hallucinations before processing (a data-altering pre-step that defaults to true). Gaps remain — it does not say whether the summary is persisted and retrievable elsewhere, whether summarization is expensive/slow, or what happens if no transcript or session exists.

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

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

The core purpose is front-loaded in one sentence, followed by one line per parameter with the parameter name leading. No filler, no restatement of the title, and every clause carries actionable content.

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

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

For a four-parameter, zero-required tool with an output schema (so return values need not be explained), this covers purpose, template choices, side effects, and defaults well. The remaining hole is pipeline context — the prerequisite that a session must be recorded/transcribed first, and whether the produced summary is stored for later retrieval.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it documents all four parameters: `session_id` (with the non-obvious empty-string = latest-session default), `template` (with all three allowed values and their intended use, which the schema does not enforce as an enum), `send_to_telegram`, and `clean_first`. This adds meaning that an agent could not recover from the bare JSON schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource — 'Generate a structured, evidence-grounded meeting summary (MoM) from a recorded meeting' — and adds scope detail (MoM templates, exact timestamped action items). This clearly separates it from the recording/transcription siblings (start_meeting_recording, transcribe_meeting) and the listing sibling (list_meeting_summaries), which produce or enumerate rather than summarize.

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

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

Usage context is implied rather than stated: it summarizes 'a recorded meeting,' but never says the recording must already be transcribed, whether prior summaries are overwritten or versioned, or when to prefer this over list_meeting_summaries. The template legend ('project_sync' technical/project status, 'standard' general, 'standup' quick sync) is useful selection guidance but reads as parameter semantics, not when-to-call-the-tool guidance.

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