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

Annotations already declare destructiveHint=true and openWorldHint=true, so the description earns credit for going further: it discloses the approval gating requirement, that only the stored plan matching approval_ref plus digest is used, that other operation kinds are rejected before anything is reserved or applied, and that spend may be affected. It does not cover retry/idempotency semantics after a partial failure.

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?

Three tight sentences, front-loaded with the approval precondition, then the plan-selection rule, then the external/spend consequence. No filler and nothing buried.

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 destructive, open-world mutation with an output schema (return values need not be described) and annotations covering the safety profile, the description supplies the missing consent, plan-binding, and rejection behavior. The only gaps are the unmentioned connection_context parameter and post-failure retry behavior.

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 must carry the load. It gives real meaning to approval_ref (selects the stored plan) and expected_plan_digest (must match that plan), which is valuable, but the third parameter connection_context is never mentioned, and format constraints are left entirely to schema patterns.

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 precise verb and resource: 'replace the destination URL on one existing Meta ad.' This distinct from the prepare sibling (ads_update_url_prepare) and from the other confirm operations (operations_confirm_ad_copy_update, etc.), and the 'After explicit user approval' clause marks it as the commit step of a two-phase flow.

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?

'After explicit user approval' tells the agent the precondition for calling, and 'Uses only the stored plan selected by approval_ref and expected_plan_digest' explains what inputs select the work. It never names the prepare tool or states what to do if no approved plan exists, so the routing is clear but not fully explicit.

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