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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false. The description earns credit beyond that by disclosing the confirm=false dry-run behavior and the ordering prerequisite for AD_CALL. It does not, however, say what gets permanently created or whether the action is immediately active for tracking.

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?

Dense but front-loaded: creation statement first, then type semantics, then prerequisites, then sibling routing. Every segment carries information, though the enum list is long and the sentence structure is run-on.

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?

An output schema exists, so return values need not be described. For a 7-parameter destructive create, the description covers purpose, key parameter semantics, prerequisites, and routing. Minor gap: no mention of what default_value does or what error/validation behavior to expect.

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 parameter meaning, and it does so for type (all six values with plain-English explanations), category (examples plus the PHONE_CALL_LEAD default for call types), phone_call_duration (unit and applicability), and confirm (dry-run). Only name, customer_id, and default_value are left to inference, though those are largely 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?

Opens with a specific verb+resource ('Creates a new conversion action') and then explicitly distinguishes itself from read/edit/primary siblings by name. An agent can route correctly without opening any schema.

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?

Explicitly states 'this tool only CREATES' and routes to list_conversion_goals for reads, update_conversion_action for edits, and update_conversion_goal for primary/biddable changes. It also gives a hard prerequisite (run set_call_reporting(call_conversion='true') before AD_CALL) and the country limitation on Google forwarding numbers.

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