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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description adds genuine context beyond that: partial-update behavior, the confirm=false dry-run switch, and the API-level restriction on pausing/removing. It does not state permissions, reversibility of a value change, or audit implications.

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 verb and scope, then enumerates parameters in a single dense but scannable sentence with a trailing NOTE and dry-run hint. Slightly long, but nearly every clause conveys a value, example, or constraint that would otherwise be missing.

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 10-param mutation tool with an output schema present, the description supplies the field semantics, value formats, dry-run mechanism, and the pause/remove exclusion. Return values are correctly left to the output schema; only permission/auth requirements are absent.

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 0% schema description coverage across 10 params, the description carries the full burden and mostly succeeds: it defines default_value + currency example, the string 'true'/'false' for always_use_default_value, the counting_type enum, both lookback params, the phone_call_duration unit and call-only restriction, and confirm. Only the two required ID params are left undetailed, which are self-evident.

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 ('Edits') plus a precisely scoped resource ('a conversion action's VALUE/COUNTING settings'), which plausibly separates it from broader siblings like update_conversion_action or manage_conversion_actions. It never names those siblings explicitly, so differentiation requires inference.

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 operating context: partial-update semantics ('only the fields you provide change') and a when-not note that pausing/removing is disabled in the API and must be done in the panel. No alternative tools are named, so routing between it and update_conversion_action is left implicit.

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