Start or finish a Gmail reply check

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

The description adds substantial behavior beyond the annotations: start is read-only and repeatable, while finish sets the last check time and changes what the next check searches. It also warns to call finish only after recording everything found, which is important operational context not captured by the schema or annotations.

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?

The description is front-loaded and organized into purpose, usage, behavior, parameters, returns, and errors. It is somewhat repetitive in restating start/finish behavior across sections, but the repetition reinforces a short two-action workflow rather than adding noise.

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 one-parameter workflow tool with no output schema, the description covers the missing return-value information directly, including the plan returned by start and {last_check} returned by finish. It also explains the key side effect of finish and the error case, leaving no important gap for correct invocation.

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% and the enum already documents start/finish, but the description goes further by explaining what start returns: since, gmail, applied, and known_message_ids. It adds meaningful semantics for the action parameter beyond the schema, though the parameter itself is simple.

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 uses a specific verb+resource+workflow framing: it begins/ends a Gmail reply check and explicitly distinguishes this framing role from freeapply_record_outcome, which records individual emails. An agent can tell exactly what the tool is for and what it is not for.

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 ordering and conditions: use start before searching Gmail, use finish only after every found email is recorded, and do not use this tool for recording an email. It also names the sibling alternative freeapply_record_outcome, so the routing decision is clear.

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