Set Flag

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It explicitly states the operation is reversible and that it is a write requiring explicit user intent, which are key traits. It does not cover failure modes or side effects, but the core behavioral aspects are disclosed.

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 two sentences, with the purpose front-loaded and the additional context (reversibility and write warning) succinctly added. There is no wasted wording, and the structure is efficient.

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 4-parameter tool with full schema coverage and an output schema, the description covers the purpose, reversibility, and intent warning. It does not explain the return value, but that is covered by the output schema. It omits potential prerequisites like folder existence, but these are not critical for basic usage. Overall, it is sufficiently complete for the tool's simplicity.

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 description coverage is 100%, so all parameters (add, flag, uids, folder) are documented in the schema. The description adds no extra parameter-level semantics beyond what the schema already provides, so it stays at the baseline of 3.

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 action ('Marque des messages') and the resource (messages), listing the specific flags (read, unread, important, replied). It also distinguishes from send_email and move_emails by name, which helps the agent differentiate from at least two siblings. The purpose is unambiguous.

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 contrasts with send_email and move_emails by noting reversibility, which implies this tool is for flag modifications. However, it does not explicitly state when to use this tool over other siblings like read_email or search_emails, nor does it provide explicit exclusions beyond the two named tools. Context is present but not comprehensive.

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