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

Annotations already declare destructiveHint=true and openWorldHint=true, and the description adds real domain context: PRESENCE stops geo-leakage, negative=True turns additions into exclusions, and removal IDs must come from ads_get_geo_targeting. It does not mention permissions or irreversibility of removals, so it does not fully exploit the destructive mutation profile.

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-loaded with the core verb and resource, then groups parameters by operation. The parentheticals are dense but each carries non-obvious information (enum values, example IDs, cross-reference), so little is wasted.

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 6-parameter mutation tool with an output schema present, the description covers every meaningful operation and parameter source. It stops short of stating whether at least one operation must be supplied or what happens if none is given.

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 0%, so the description carries the full burden and does so: it supplies the accepted values for positive_geo_target_type (which the schema does not enumerate), explains that add_location_ids are geo-target constant IDs with concrete examples (2276 = Germany, 2040 = Austria), documents the negative flag's effect, and points remove_criterion_ids to their source.

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?

Uses a specific verb plus resource ('Geo-Targeting einer Kampagne ändern') and enumerates the three concrete operations (set positive_geo_target_type, add locations, remove criteria). It also names the sibling tool ads_get_geo_targeting as the source of criterion IDs, so an agent can distinguish it from related geo tools without opening a schema.

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?

Explains the conditions for each mode: use positive_geo_target_type to switch between PRESENCE and PRESENCE_OR_INTEREST, add_location_ids to add, remove_criterion_ids (fetched via ads_get_geo_targeting) to remove, and negative=True for exclusions. There is no explicit 'do not use this for X' exclusion versus other siblings, which keeps it just 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.