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

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, so the write/external nature is known. The description adds context beyond that by identifying the destination of the write (the Deenwise sales team) and the consent precondition, which is the key behavioral safeguard. It does not say what a successful submission returns, whether duplicate requests are deduplicated, or whether the contact is immediate, which would matter for a non-idempotent outbound action.

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?

Two sentences, no filler, and the operative constraint (the ONLY-call-after-consent rule) is placed prominently. Every clause earns its place.

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 an 11-parameter, non-idempotent outbound submission tool with no output schema, the definition covers only purpose and consent. An agent gets no sense of the consequence of submission, what confirmation the caller sees, or how the mostly-undocumented parameters (interests, business_type, current_apps) should be populated.

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?

With 11 parameters and only 27% schema description coverage, the description is expected to compensate, but the only field it discusses is consent — and that is already documented in the schema with nearly identical wording. Business type, interests, current_apps, phone, city and the rest receive no guidance about required format, relevance, or how they affect routing to the sales team.

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 and object: it 'passes a business owner's request for a demo or call-back to the Deenwise sales team', which clearly frames this as a lead-submission action. It is implicitly distinguishable from the informational siblings (deenwise_overview, deenwise_plans) because it is the only one that transmits data outward, but no sibling is named to make that contrast explicit.

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?

It gives a strong, explicit gating condition: 'ONLY call this after the person has clearly agreed that Deenwise may contact them'. That functions as a when-to-use and a when-not-to-use rule in one clause. It stops short of naming alternatives (e.g. answer questions with deenwise_plans first) or stating what to do when consent is absent.

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