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

Goes well beyond the annotations by disclosing that this contacts a real customer, that retries with the same key are deduplicated, that pending/unknown writes are blocked, and that provider acceptance does not prove customer delivery. These are substantive operational facts the readOnlyHint/idempotentHint flags cannot convey. It stops short of stating rate limits or failure/retry-backoff behavior, and it is consistent with idempotentHint=true and destructiveHint=true (outbound contact is irreversible).

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?

Five short sentences, each carrying distinct information, with the action and scope front-loaded before prerequisites and caveats. No filler and no restatement of the title.

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 send tool with an output schema available, it covers the critical unknowns: authorization role, idempotency contract, delivery uncertainty, and the attachment limitation. Minor gaps remain around where business_id/lead_id originate and any rate or quota limits.

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 only fully explains idempotency_key (stable, dedup on retry). business_id, lead_id, and message are named only indirectly ("existing... lead", "text reply"), leaving format, provenance, and length constraints to the schema alone.

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 ("Send") and resource ("text reply") with a clear scope constraint: inside an existing Google LSA message lead via the Ads API. The lead-scoped framing implicitly separates it from generic send_message/send_sms siblings, but no sibling is named explicitly, so the differentiation is inferred rather than stated.

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?

Provides prerequisites (current business admin role, stable idempotency_key) and an exclusion (attachments unsupported), which narrows when it applies. However, it never says when to choose this over send_message or send_sms, nor where lead_id comes from; usage is implied by the LSA-lead scope rather than spelled out.

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