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

Beyond the annotations (openWorldHint, destructiveHint=false), the description discloses that an external party will actually contact a US business, that no account is created and no charge occurs, and that the returned status_token is one-time. It also converts idempotentHint into an actionable instruction, which is genuine added context rather than a restatement.

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, front-loaded with the action and the two intent values, with no filler. The consent and no-charge/no-account clauses are compact and each adds information.

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 write-only lead-capture tool with no output schema, the definition covers side effects (external contact, no account, no charge), safety (consent, idempotency) and the return values (tracking reference, one-time status_token). It stops short of naming get_demo_status as the consumer of the status_token or clarifying the conditional partner_type parameter, which an 11-parameter tool would benefit from.

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% across 11 parameters, so the description must carry the burden. It only explains the 'interest' enum semantics (demo vs partnership), implies 'consent_to_contact' via the consent sentence, and covers 'idempotency_key'; the other eight parameters (contact_name, business_name, phone, email, message, industry, best_time, partner_type) get no meaning, including whether partner_type is required when interest=partnership.

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?

The description names a specific verb ('Ask VoiceDesk AI to contact') and resource (a US business) and disambiguates the two intent modes by mapping each to its enum value ('interest=receptionist_demo', 'interest=partnership'). It does not distinguish this from sibling tools like create_onboarding_request or check_compatibility, so an agent still has to infer which request tool to pick.

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?

The prerequisite 'Only with the owner's consent' is stated and the retry guidance ('Send an idempotency_key to make retries safe') is actionable. However, there is no explicit comparison against create_onboarding_request or guidance on when a partnership inquiry should go here versus elsewhere; usage is implied rather than routed.

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