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

Annotations already state the tool mutates (readOnlyHint=false), is idempotent, and is non-destructive; the description adds the key partial-update behavior ('Only provided fields are updated') and the return contract ('Returns the updated campaign object'). These are meaningful behavioral details not available in the structured annotations. There is no contradiction between the description and annotations.

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?

Two short sentences carry the entire semantics: what is updated, what the update means, the partial-update rule, and the return value. There is no filler or redundant restatement of the name or schema. It is well structured and front-loaded.

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?

The combination of description, the detailed schema description for outreachIntents (override/fallback/ordering), and annotations covers safety, idempotency, field semantics, and return value. Without an output schema, 'Returns the updated campaign object' is sufficient. The only minor gap is the absence of explicit guidance about when not to use this tool, which is more usage guidance than contextual completeness.

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?

With only 25% schema description coverage, the description compensates by naming all updatable fields and clarifying that outreachIntents means 'why this campaign writes to people.' It also communicates the optionality/partial-update behavior ('Only provided fields are updated') that the schema does not state at the top level. campaignId is left to inference, but its role is self-evident from the name and required flag.

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?

The description opens with a specific verb and resource ('Update a campaign's') and enumerates the exact mutable fields—title, description, and outreachIntents—which distinguishes it from sibling tools like create_campaign, archive_campaign, or update_campaign_weight. The parenthetical also clarifies the otherwise ambiguous 'outreachIntents' concept. There is no mistaking what operation this performs.

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?

The intended use (modify an existing campaign's content fields) is implied by the verb and the field list, but the description never explicitly says when to prefer this tool over related siblings such as create_campaign or update_campaign_weight. It offers no exclusionary guidance or alternative routing. This is adequate but left to inference.

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