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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false, openWorldHint=false), and the description adds real context: the brief is server-generated with no AI inference, has a defined content set, and only accepts events from the caller's own imported calendars. It does not cover edge behavior such as passing two identifiers at once or what happens with an unknown id, so it stops short of full transparency.

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?

Dense but well structured with no filler — content list, then parameter routing, then the ambiguity rule. The only weakness is front-loading a Ukrainian example phrase before the tool's action is named, which delays the core statement for an English-reading agent.

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 compensates by enumerating what the brief contains, which is what an agent needs to decide whether to call it. Combined with the mode selection and ambiguity handling, nothing essential for correct invocation 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 description coverage is 0%, so the description carries the full burden and does so: it explains each of the three parameters' meaning and resulting behavior, states they are mutually exclusive alternatives, accepts 'any spelling' for query, and warns that an ambiguous query returns candidates rather than a guess. That is meaning well beyond the bare type definitions.

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 user-voice framing then states exactly what the tool returns: a server-built (no AI) pre-meeting brief containing identity, how you met, the last 2 timeline entries, open reminders, and a birthday within 14 days. It also differentiates two modes of operation (whole-meeting brief vs. single-person slice), so an agent can tell what it gets without reading the schema.

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?

Explicit routing rules: 'Pass ONE of' and then the effect of each key — event_id yields the full meeting brief for every known attendee, contact_id or query yields that person's part. It also gives an ambiguity policy ('ask, never pick') and constrains event_id to the caller's own imported calendars, referencing where such ids come from.

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