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

readOnlyHint=true is already declared by annotations, so safety is covered. The description adds almost nothing behavioral beyond implying waiting; the substantive details (wait up to 45s, cursor reset semantics) live in the schema, not the prose, leaving blocking behavior, timeout outcomes, and return shape unexplained.

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?

The description is short but fragmented into cryptic clauses separated by semicolons, so terseness comes at the cost of parseability. Front-loading 'Newest events' is the one structural strength, but the rest reads like shorthand notes rather than a usable definition.

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 10-parameter, zero-required tool with no output schema, this is significantly under-specified. An agent cannot determine default behavior, how the wait/interaction parameters combine, or what a response contains from the description alone.

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 60%, and the description does map to several parameters ('after your cursor', 'about=me', 'kinds', 'mail'), adding marginal meaning such as the about=me semantics. But roughly half the parameters (seen, limit, catch_up, mail_after) get no prose support and are the ones least documented in the schema.

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 title 'Events, and waiting for them' combined with 'Newest events, or after your cursor' and 'the wait' conveys that this retrieves events and can block waiting for them. However, the description is telegraphic and never states the verb plainly, and the 'new_mail' fragment does not correspond to any parameter name, adding confusion rather than clarity.

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?

'new_mail: unread mail' and 'mail: the wait' hint at mail-related usage but give no explicit when/when-not guidance. With siblings like observe and inbox that plausibly overlap on event retrieval, the description offers no routing signal to distinguish them.

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