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

The description goes far beyond the annotations (readOnlyHint, openWorldHint). It discloses authentication requirements ('needs your API key'), the cursor semantics, the wait behavior and its bounds, the guarantee that 'nothing is lost', and the payload structure including the 'untrusted' data warning. It also explains the return format and the next_cursor usage. No contradiction with annotations; in fact it reinforces the read-only and open-world nature.

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?

Although long, every sentence carries essential information: purpose, event types per role, payload shape, parameter details, and security guidance. The structure is logical: starts with the core function, then the cursor, then event categories, then payload, then parameters, then the untrusted warning. It is dense but not verbose, and front-loads the most critical info.

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 must explain the return format, and it does: 'Each event is {id, type, profile_id, created_at, payload}'. It also covers all parameters, the meaning of next_cursor, the wait behavior, and the untrusted payload warning. For a tool with three parameters and a detailed event type list, nothing essential is missing. An agent can call this tool correctly with complete confidence.

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 description adds substantial meaning to all three parameters. For 'after', it explains the format (last event id like evt_88), that omitting it gives the whole history, and how 'next_cursor' relates. For 'limit', it specifies the range 1–100 and the default 50. For 'wait', it explains the purpose (hold open until an event arrives for polling) and the valid range, plus the invalid_input error for out-of-range. The schema descriptions are mostly redundant but the description enriches them with real usage context.

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 clearly states the tool's function: it returns the event stream for the user's profile, oldest first, with cursor-based pagination. It distinguishes itself from the many sibling query tools by being the comprehensive event feed covering all event types for both sellers and buyers. The verb 'stream' and resource 'events' are specific, and the description enumerates exactly what events are included.

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?

The description explains when to use this tool: to retrieve all events for the profile after a cursor, and it even explains the polling use case with the 'wait' parameter ('an agent with no server can poll without hammering us'). However, it does not explicitly name alternative tools to use instead for narrower queries, though the sibling list (e.g., getBids, getQuestions) implies those are for specific data. A 4 because the context is clear but no explicit exclusions are given.

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