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

Goes well beyond the annotations: status REMOVED is irreversible, pausing/HIDDEN is not supported by the Google API, default_value is forcibly applied to ALL conversions and overrides tag/upload values, 'success' only means the API did not reject, and there is documented automatic idempotent retry (twice, 1s/2s) with a 'retries' field and google_ads_error otherwise. This is exactly the extra context the destructive/openWorld hints cannot carry.

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-loaded with the core action, then organized per parameter with the highest-risk facts (irreversible removal, verification requirement, retry behavior) placed before the mundane ones. A few sentences (the retry mechanics) are dense but each earns its place; the mixed German/English naming adds minor noise.

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 7-parameter destructive mutation with an output schema, the description covers everything an agent needs to call it safely: partial-update scope, irreversible status, forced default values, dry-run mode, post-call verification, and retry/error semantics. Return-value explanation is correctly left to the output schema apart from the notable 'retries' field.

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 coverage is 0%, so the description must carry the load and mostly does: primary_for_goal, default_value, status, validate_only, and workspace are all explained with semantics and edge cases. 'name' and 'conversion_action_id' are only implied by the opening sentence, which keeps it from a 5.

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 ('Ändert eine bestehende Conversion-Aktion') and immediately pins down the partial-update semantics with '(nur übergebene Felder)'. It never explicitly contrasts with ads_create_conversion_action, but the word 'bestehende' plus the required conversion_action_id makes the create-vs-update boundary clear enough.

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 concrete usage contexts: promote a qualified lead to primary, demote a contact form reversibly to secondary, dry-run with validate_only, and read back with ads_list_conversion_actions. It does not state when to prefer this over other paths or any prerequisites (permissions, account state), so it stops short of full alternative routing.

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