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

Annotations only declare readOnlyHint, and the description adds useful behavioral context: data is already synced, results are newest-first, the call is fast and does not invoke Granola. It does not discuss staleness or auth, but that is not required for a simple read-only list.

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?

Three sentences with no filler: the first front-loads the resource, ordering, and output fields; the second maps parameters to behavior; the third gives the follow-up route. Every sentence contributes.

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 simple read-only list with four optional, fully documented parameters and no output schema, the description gives the important return shape, sort order, parameter semantics, and next-step tool. Nothing an agent needs 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?

The schema already covers all four parameters (100% coverage), so the baseline is 3. The description adds plain-language semantics for days, query, and attendee, explaining filtering behavior beyond the schema's field descriptions. Only limit is left entirely to the schema, which is acceptable.

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 ('List ... Granola meeting notes'), states the result ordering ('newest first') and enumerates returned fields (title, time, attendees, space, link). It also names the sibling get_granola_note for drilling into one meeting, so an agent can distinguish list from detail retrieval.

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?

It clearly signals this is the lightweight path over already-synced notes ('Fast, no Granola call') and instructs follow-up with get_granola_note for summaries/transcripts. It does not explicitly contrast with search_granola_transcripts or state when not to use the tool, but the primary alternative is named.

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