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

Annotations establish non-read-only, non-destructive, non-idempotent, open-world behavior, and the description adds genuinely useful context beyond them: nothing changes on Google (draft-only), the platform limit of 9 additional categories, and the human-approval gate before publishing.

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-loads the verb and resource, and each of the four sentences carries distinct information (scope, id source, limit, draft/publish workflow). Slightly dense, but nothing is padding.

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?

No output schema exists, but the description fills that gap by telling the agent what the call returns (a draft to be shown verbatim) and what must happen before it takes effect. Nothing needed to invoke 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 description coverage is 100%, so add/remove semantics and the gcid format are already documented. The description implies where ids come from but adds no syntax detail beyond the schema; baseline 3 is appropriate.

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?

States a specific verb (Draft adding/removing) and a narrowly scoped resource (ADDITIONAL categories), explicitly distinguishing from the primary category, which lands it apart from siblings like propose_services or propose_attributes.

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?

Names the id sources (find_google_categories, my_google_profile), states the exclusion (primary category is never changed), and prescribes the follow-up workflow: show the draft word for word, then publish_change only after owner approval.

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