Rename a folder or label

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

Annotations already declare non-read-only, non-destructive, non-idempotent and open-world, so the safety profile is partly covered. The description adds material context the annotations cannot: protected mailboxes are refused, type and parent are preserved, and a confirmation gate must be satisfied via confirmed=true. It doesn't say what happens when confirmation is refused or when the new name collides.

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?

Three tightly packed sentences: semantics first, refusal list second, gating last. Every clause carries operational information and nothing is repeated from the schema.

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 gated rename mutation with no output schema, the description covers refusals, in-place semantics, and the confirmation workflow. Remaining gaps (what a rejected confirmation returns, duplicate-name handling, whether dry_run can be combined with confirmed) are modest.

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 75%, with name, new_name and dry_run well documented in-schema. The description supplies the missing piece for 'confirmed' (it must be set true after user confirmation), but leaves the confirmed=false path and collision behavior undefined. Baseline 3 fits given the schema does most of the work.

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?

Names a specific verb+resource (rename a folder or label) and immediately clarifies the semantics: 'a label stays a label and a folder keeps its parent.' An agent can distinguish this from move_to_folder by the explicit 'where it stands' framing, though no sibling is named directly.

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?

Gives a clear gate ('confirm the old and new names with the user, then call with confirmed=true') and enumerates the refusal cases (INBOX, Sent, Drafts, Trash, Spam, Archive, All Mail). It never points to an alternative sibling such as create_folder_or_label for the case where the target doesn't exist, which keeps it short of a 5.

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