google_ads_schedule_targeting_update

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

With no annotations, the description carries the full burden and does most of it: it declares the operation mutating, discloses that new criteria default to start_minute/end_minute=ZERO (on the hour), and warns that reversal requires calling again with inverse operations. It stops short of saying what happens on partial failure or whether removed criteria lose history permanently, and says nothing about required Google Ads permissions.

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?

Five short sentences, zero filler, with the mutating warning and operation contract front-loaded before the alternative-tool pointer at the end. Each sentence contributes a distinct fact: action, return shape, default behavior, reversibility, precondition, sibling.

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 mutation tool with no annotations and no output schema, the description supplies the return shape ('[{resource_name}] — one entry per operation, adds first, then removes'), the mutation/reversibility profile, and the default minute behavior. What remains uncovered is failure handling on a partially-invalid batch and any auth/approval expectations, though the schema's approval and reason fields partially compensate.

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 per-parameter meaning is already documented and 3 is the baseline. The description adds one genuinely new fact not in the schema — the ZERO minute default — and restates the anyOf constraint, but adds nothing about ordering semantics of the two arrays beyond the return-value note.

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 pair (add and/or remove) applied to a specific resource (ad-schedule criteria on a Google Ads campaign) with the batching scope called out ('in a single mutate'). It explicitly names the sibling it is not — google_ads_schedule_targeting_list — so an agent can disambiguate without opening either 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?

Gives the selection rule outright ('For the read-only listing use google_ads_schedule_targeting_list') and states the invocation precondition ('At least one of add_schedules / remove_criterion_ids must be provided'). The only missing element is prerequisite discovery of campaign_id, which the schema already routes to google_ads_campaigns_list.

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