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

Adds real behavior beyond annotations: the 20% cap on the daily budget and the deferred-mutation semantics (nothing changes until confirm=true). Annotations already flag readOnly=false/destructive=false, but the cap and staging behavior are meaningful extras not derivable from structured fields.

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?

Four tight sentences, front-loaded with the action, then param sourcing, then the cap, then the confirmation gate. Every sentence adds a distinct constraint with no filler.

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 33-parameter tool with zero schema descriptions, the description covers only the core happy-path params and ignores the bulk of the schema. Output schema exists so return values need no explanation, but the parameter ambiguity is a major gap that the description does not close.

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% across 33 parameters, so the description carries the full burden, yet it only names campaign_id and 'the account id'. The many other params (action, metric, threshold, rule_id, dry_run, etc.) are left entirely undefined, leaving an agent unable to tell which matter for a budget change.

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: 'Create a pending daily-budget change for a selected Google/Meta campaign.' The 'budget' resource naturally separates it from the sibling automate_propose_pause, though it never names that sibling explicitly.

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 clear context: source campaign_id and the account id from the *_get_campaigns rows, and routes the follow-up step to automate_confirm_action with confirm=true. No explicit when-not-to-use or exclusion, but the workflow positioning is clear.

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