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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=false; the description goes beyond them by disclosing that the export is private, that it returns a completed job with an authenticated, expiring download link, and that it does not re-process audio or consume minutes. That cost and link-lifetime context is genuinely useful, though it says nothing about permissions or failure modes.

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?

Two sentences, front-loaded with the usage trigger, and every clause carries information (formats, scoping, privacy, non-reprocessing). It is dense but slightly overloaded with parenthetical formats where a single list would read faster.

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?

An output schema exists, so explaining return values is optional, yet the description still summarizes the result (a completed export job with an authenticated expiring link). Combined with the format/section coverage and the explicit non-share clarification, an agent has everything needed to call this correctly.

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?

With 50% schema coverage the description must compensate, and it does: it enumerates the format targets (PDF, Word/docx, Markdown, text, JSON) and explains that sections can be chosen or omitted for the whole document, clarifying the sections parameter. It does not clarify revision's precondition semantics beyond what the schema says, and meeting_id remains undescribed.

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?

Specific verb (export) plus resource (a finished meeting) and explicit output formats and section scoping. It also carves out a distinction from a public share link, but it never names or distinguishes against the actual sibling tools (fetch, meetnotes_get_transcript, meetnotes_list_recordings), so full sibling differentiation is absent.

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?

The opening 'Use this when the user wants to download, save or share...' gives a clear trigger condition, and the 'it is not a public share link' clause rules out one near-miss. There is no explicit guidance on when to prefer meetnotes_get_transcript or other siblings instead, so exclusions are partial.

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