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

Beyond the readOnly/idempotent annotations, it discloses pagination via nextCursor, the size cap implied by 'a page at a time', the meaning of isLive, and that resumeCursor hands off to get_live_transcript so only subsequent speech is returned. That is exactly the behavioral context annotations cannot carry.

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?

Purpose and scoping come first, then detail modes, then pagination and live state — a sensible front-loaded order with no filler. The example-query list is slightly verbose relative to its value, but each clause still carries information.

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?

With a full schema and an output schema present, the agent needs only the paging model, the detail trade-off, and the live-recording handoff — all supplied. Nothing required to call it correctly is missing.

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 coverage is 100%, so the baseline is 3, but the description adds intent the schema lacks: which detail mode suits summarising versus citations, and that 'full' is the default. Cursor and limit handling are only loosely described ('continue with nextCursor'), leaving the rest to the 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?

States a specific verb and resource ('returns the transcript of one recording by sessionId') plus the scoping unit (one recording, paged). The detail-mode explanation and the pointer to get_live_transcript for live continuation separate it from siblings such as search_all_transcripts and show_transcript.

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?

Names concrete trigger queries in two languages ('what did we discuss', 'fasse die Vorlesung zusammen') and tells the agent when to switch to get_live_transcript with resumeCursor. It stops short of excluding sibling tools such as show_transcript or search_within_recording, so the routing is clear but not exhaustive.

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