get_updates

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

With no annotations, the description carries the full burden and does disclose real behavior: ordering is oldest-first, items are fetched after a cursor, and iteration should continue while has_more is true. It omits what an event contains, whether requires_project access is scoped, rate limits, and whether the caller's own actions appear in the stream.

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?

Two short sentences with the read semantics and the pagination loop front-loaded; nothing is padded or redundant. It borders on under-specification, but every sentence does carry operational weight.

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 annotations and no output schema, the description partially compensates by naming the return fields next_cursor and has_more and describing the loop that consumes them. It still leaves the required project_id scope and the limit parameter unexplained, which is a material gap for a multi-tenant event feed.

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 0%, so descriptions must compensate for all three parameters, but only after_event_id is obliquely implied by 'after a cursor' — and the description calls it a cursor while the schema calls it an integer event id, which is a naming mismatch the agent must resolve. project_id and limit receive no meaning at all, including no explanation of limit's default of 30 or its interaction with has_more.

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 ('Read events') plus the ordering and cursor anchor ('oldest first after a cursor'), which is far more than the bare name get_updates conveys. It does not distinguish itself from siblings like get_context or search_context, so the agent has to infer the boundary from the name alone.

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?

'continue while has_more' gives clear in-loop pagination guidance, which is genuinely actionable. However, there is no statement of when to choose this over get_context/search_context, nor any prerequisite or exclusion, so cross-tool selection is left implied.

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