Manage comments

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

The description goes well beyond the annotations: it discloses permanent deletion, the inability to anchor new comments, pagination behavior, tombstone handling, resolve semantics, and the OAuth scope requirement with a concrete 403 failure mode. These are behaviors the agent cannot infer from the schema or annotations alone.

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 dense but every sentence contributes actionable detail. It is structured as a single paragraph with semicolon-separated action clauses, which is readable though slightly run-on; it front-loads the core purpose before diving into per-action specifics.

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 tool with no output schema, the description covers the critical input-side context: each action's parameters, pagination, auth requirements, and destructive behavior. It does not describe the exact response format for get/list, but for selecting and invoking the tool correctly, the missing return details are a minor gap.

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?

Although schema coverage is 100%, the description adds crucial cross-parameter semantics: which parameters apply to which actions, that content must be plain text, that resolve only makes sense with reply, and that comment_id comes from list results. This bridges the flat schema into per-action usage rules.

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 names the resource ('comment threads on the presentation file') and the specific actions ('list', 'get', 'create', 'reply', 'delete'), making the tool's purpose unmistakable. It also distinguishes itself from generic Drive access and from sibling tools that manipulate slides, shapes, or text.

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 gives clear action-by-action usage conditions, including required parameters and caveats such as 'create ... starts a new unanchored thread' and 'delete ... permanently removes the thread'. It does not explicitly name an alternative sibling tool, but none exists for comments, and the 'scoped to this one file' note helps prevent misuse of the underlying Drive API.

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