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

Goes well beyond the annotations (destructive/openWorld/idempotent) by disclosing state-dependent mutability, the exact error code for rejected edits, that daily budget is pushed to the provider and therefore changes spend, and that human approval is required. The '[publish · spend]' tag front-loads the risk 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?

Dense and front-loaded: identifiers first, then the draft-vs-published state rule, then the error code and approval note. Slightly packed with parentheticals, but every clause adds information an agent needs.

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 12-parameter mutation with no output schema, it covers the critical decision points: which fields are legal in which state, what happens on violation, and that approval gates execution. It omits what the tool returns and whether id or uuid takes precedence if both are supplied.

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 it only annotates 4 of the 12 parameters (id, uuid, title, daily budget). The remaining fields — goal, website id/uuid, creative, targeting, start/end date, custom url — get no explanation of format or semantics beyond their names.

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?

Names a specific verb ('Edit') and resource ('an ad campaign'), names both accepted identifiers (`ads_campaign_id` or `ads_campaign_uuid`), and states the partial-update contract ('only the given fields change'). This distinguishes it cleanly from publish_ads_campaign and create_ads_campaign in the sibling list.

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 explicit conditional guidance: everything is editable before the campaign exists on the provider, but after publishing only title and daily budget are editable, with the failure mode named (ERR_ADS_CAMPAIGN_PUBLISHED_READONLY). It does not, however, route the agent to alternatives such as publish_ads_campaign or activate_ads_campaign when the precondition is unmet.

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