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

Annotations only cover the read/write/open-world/idempotency profile; the description adds substantial non-obvious behavior: the one-time Google Ads ToS acceptance that blocks every create until done, pre-call length validation to avoid round trips, and webhook delivery of leads. This is exactly the extra context annotations 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?

Long but dense and front-loaded: the resource is defined first, then the required-field rules and length limits, then enums, then the gotchas. A few editorial asides ('the one that surprises people') add flavor rather than confusion, but slightly exceed strict conciseness.

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 complex 19-param mutation tool whose safety profile is in annotations and whose return shape is covered by an output schema, the description supplies the missing operational context — required fields, validation limits, enum values, the ToS blocker, preview mode, and the webhook alternative. Nothing essential to calling it correctly is 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?

Schema coverage is 0% on 19 params, so the description carries the burden and mostly does: it explains business_name/headline/description/privacy_policy_url requirements and the 25/30/200 char limits, enumerates cta and fields values, defines the questions 'question|answer|...' format, and covers post-submit and webhook params. It omits name, final_url, and cta_description, so not fully complete, but the critical and surprising constraints are documented.

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 (Creates) and resource (Google Ads LEAD FORM), and even explains what the artifact is (opens inside the ad, collects name/phone without a website visit). An agent can immediately distinguish it from create_meta_lead_form and the list_lead_form_submissions sibling.

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 routing context: webhook_url pushes leads in real time, 'without it, read them with list_lead_form_submissions', and confirm=false yields a preview. Lacks an explicit statement of when NOT to use it versus the Meta/other lead-form creators, but the Google Ads scoping is implicit and the alternatives are named.

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