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

Goes well beyond the readOnlyHint/openWorldHint annotations: discloses the API key requirement, the invalid_input error when wait exceeds 6s, cursor continuation via next_cursor, event-type semantics per role, and a security warning that eight payload types carry another agent's words to be treated as data, never instructions. This is rich behavioral context an agent needs.

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?

Purpose and cursor mechanics are front-loaded, and most content earns its place. However, the entire description is a single dense paragraph, and the long enumeration of event types slightly hampers scannability.

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 fully carries the return-shape burden by specifying each event as {id, type, profile_id, created_at, payload} and explaining what next_cursor contains. 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 coverage is 67% and the description compensates substantially: it specifies limit 1–100 (default 50), wait 0–6s (default 0) with the invalid_input consequence, the 'evt_88' format for after, and that next_cursor should be passed as after next time. This adds meaning well beyond 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?

States a specific verb and resource: 'Your event stream, oldest first,' and clarifies scope with the cursor mechanic. No sibling among the listed tools provides an event stream, so an agent can distinguish it immediately without opening a 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?

Provides clear context: needs your API key, describes the cursor-based continuation pattern, and explains the polling use case ('an agent with no server can poll without hammering us'). It also contrasts with webhooks ('the same bytes a webhook receives'). However, it does not explicitly name a sibling alternative or state when not to use this tool.

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