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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's value-add is pagination mechanics (~8k tokens per page, cursor chaining) and the prompt-injection warning to treat transcript text as data, never instructions. That is meaningful behavioral context beyond structured fields, though auth/permission requirements are unstated.

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?

Four tight sentences, front-loaded with what is returned before filters and prerequisites. The injection warning is placed last but is short and unambiguous. No wasted wording.

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 no output schema, the description carries the burden of explaining the return format (timestamped turns, cursor for next page) and it does so well, plus it documents the filtering surface. The main residual gap is that the required 'id' parameter is never characterized (meeting ID), but that is minor given the search_meetings pointer.

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 only 40%, so the description must compensate. It clarifies that the time range is 'in seconds' and that the speaker filter is by name, but leaves 'id' and the from/to relationship to inference. Partial compensation yields a baseline 3.

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+resource ('Read a meeting's transcript') and goes further to describe the return shape (timestamped speaker turns, ~8k-token pages) and available filters. It is clearly distinguishable from siblings like search_meetings, which it explicitly routes the agent through first.

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?

Explicitly says 'Use search_meetings first to find the meeting,' giving a concrete prerequisite and naming the alternative. It also explains the pagination loop (pass the cursor named in the previous page). It does not state when NOT to use it, e.g. summary-only needs (get_recap/get_meeting), so it stops short of full when/when-not guidance.

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