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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds a genuinely non-obvious semantic caveat: meeting subtype counts are lifecycle events, so the same meeting appears in both booked and held and must not be summed as distinct meetings. That is exactly the kind of counting pitfall that prevents wrong answers.

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?

Front-loaded with purpose, then requirements, then routing, then the counting caveat, then the transcript handoff — a sensible priority order with little filler. The meeting-count sentence is long but earns its space because it prevents a real aggregation error.

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 29-parameter aggregation tool with an output schema and rich annotations, the description covers purpose, required inputs, type routing, association filtering, and the key counting pitfall. Pagination/grouping mechanics are left to the schema, which is acceptable given group_by and page_size are documented there.

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 only 41% schema description coverage across 29 parameters, the description must compensate; it does explain engagement_type families and the association filters (deal_ids/company_ids/contact_ids) conceptually, plus the transcript ID pointer. But it is silent on many undocumented parameters (detail, remove_duplicates, show_unassociated, pipeline_stages, group_page_size), leaving half the surface to be inferred from names.

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 concrete verb ('Inspect') with the resource set (emails, meetings, calls, communications, plus deal/lead events) and the analytical intent (buyer responses, rep activity). It also distinguishes the engagement_type families, so an agent can tell which records come back. It stops short of naming sibling analytics tools like get_deal_timeline or get_forecast as alternatives.

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 states prerequisites ('requires an activity type and date range'), gives a routing rule for the confusing case ('use meetings, calls, emails, or communications for associated activities' rather than deal/lead types), and points to get_transcript for transcripts. No guidance on when to prefer this over get_deal or get_deal_timeline, which is the remaining gap.

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