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

Annotations only cover the safety profile (readOnly/idempotent/non-destructive/openWorld); the description adds the non-obvious behaviors an agent actually needs: the ~50 s wait ceiling, the possible status values, the pending permission request and last-error fields, media url refresh, and the lastEventId cursor contract for resuming.

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?

Front-loaded with the core purpose in the first five words, then branches cleanly into wait and non-wait behavior. The single dense paragraph repeats a bit of what the schema already documents (limit, media), which keeps it short of a 5.

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 and five parameters, the description carries the return-shape burden well: it enumerates title, status, pending permission request, last error, turns and media status/urls, plus the underlying endpoints. Nothing an agent needs to call it correctly 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 100%, so baseline is 3, but the description adds real meaning beyond the field docs: it ties 'after' to a lastEventId produced by an earlier flow_agent_chat / flow_agent_get_chat call, and explains that wait governs whether the other params apply. It adds genuine usage semantics rather than restating types.

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?

"Read a Flow agent chat" is a specific verb+resource, and the description immediately differentiates this read tool from the sibling write path (flow_agent_chat) and the list path (flow_agent_list_chats) by spelling out the per-chat return payload. An agent knows exactly what it will get back 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?

It gives explicit operational guidance for the two modes: wait:true to follow a live turn and fetch 'the rest of a turn still running', and the default no-wait read. What is missing is sibling routing — it never says to prefer this over flow_agent_list_chats or flow_agent_chat in a given situation.

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