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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false. The description goes beyond them by disclosing the guard condition (rejects when status != 'draft'), the field caps (15 headlines, 4 descriptions), and that negative keywords append to an existing list. It does not state whether multi-field edits are atomic or how failures are reported, so it stops short of full transparency.

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 core action and scope, then uses bullets for editable fields, then closes with usage routing. Slightly redundant in restating the not-yet-pushed condition twice (scope line and rejection line), but every section earns its place and it is easy to scan.

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 7-parameter mutation tool with no output schema, the description covers scope, editable fields, limits, sibling routing, and rejection behavior well. The one gap is that with no output schema present, it says nothing about what a successful edit returns or confirms, leaving the agent to infer the response shape.

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 high (86%), so the schema carries most parameter meaning and the baseline is 3. The description adds value by organizing the seven parameters into campaign-level versus ad-group-level buckets and clarifying that destinationUrl is the landing page and addNegativeKeywords appends rather than replaces, framing not present in the schema itself.

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 and resource (Modify a campaign draft) plus the crucial scope qualifier that it lives in the DB and has not been pushed to Google Ads. It enumerates the editable campaign-level and ad-group-level fields, and explicitly names save_campaign_draft as the tool it is not, so an agent can distinguish it from siblings 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?

Explicit when-to-use ('Use adGroupUpdates whenever the user wants to add missing headlines, round out an ad group to 15 headlines, or add high-intent keywords'), explicit when-not ('DO NOT rebuild the campaign via save_campaign_draft!'), and a preconditions rule ('Rejects if the draft has already been pushed... edit there via pause/budget/keyword tools'). All routing decisions are spelled out.

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