list_flow_events

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds behavior the annotations cannot convey: results are ordered oldest-first, ids are monotonically increasing, and cursors are durable across runs — exactly what an agent needs to reason about a sync loop.

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?

Four short sentences, no filler, with the core scope stated first and the ordering/cursor guarantees following. Every sentence carries information an agent would otherwise have to guess.

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 7-parameter read tool with no required params and no output schema, the description covers ordering, cursor durability and the key parameter gotcha. It is slightly thin on how filters like since, type and starting_after interact, and on the shape of the returned feed, though the schema implies a next_cursor.

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 100%, so the baseline would be 3. The description earns more by warning "use flow_session, not session_id" — a genuine trap since additionalProperties is false and an invented session_id would fail — and by explaining that starting_after is a durable high-water mark rather than just "the next_cursor from the previous page."

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?

"List flow events across sessions" gives a specific verb and resource, and "every session event in one feed, oldest first" clarifies the scope and ordering. It does not explicitly contrast with the nearby list_flow_session_events or list_flow_sessions tools, so the agent has to infer that this is the cross-session feed.

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 line about starting_after being "a durable high-water mark for a sync loop" supplies one concrete usage pattern, which is real guidance. However, there is no statement of when to prefer this tool over list_flow_session_events or list_flow_sessions, and no exclusions or prerequisites.

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