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

Annotations only cover the safety profile (readOnly false, idempotent true, openWorld true), yet the description adds real behavioral context: the return payload (reference number and expected contact time), the negative guarantees (nothing is applied for, no credit check), and explicit idempotency semantics ('retries with the same idempotency_key return the original reference instead of creating a second enquiry'). That is exactly the kind of detail 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?

Four sentences, front-loaded with what the tool does, then the gating condition, then the return/no-side-effect guarantees, then idempotency. The quoted consent wording is verbose but load-bearing, since it is the exact text the agent must obtain.

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 13-parameter, high-stakes, externally facing submission tool it covers the essentials: consent gating, the collection-notice cross-reference, downstream contact channels, absence of credit checks, return shape and retry behavior. With an output schema present and annotations covering safety, nothing material is left for the agent to guess.

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 92%, so parameters are largely self-documenting and the baseline is 3. The description goes beyond that by embedding the literal consent wording that the consent parameter depends on and by clarifying that idempotency_key exists to collapse retries, adding meaning the schema's terse descriptions only hint at.

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 resource (sends a finance enquiry to a licensed broker) and spells out the downstream effect (broker contacts by phone, SMS and email). Combined with the consent precondition, it is clearly the terminal submission action rather than a lookup like check_fit, so an agent can separate it from siblings without opening a 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?

The precondition is explicit and unusually precise: use only after the person has agreed to the quoted consent wording. That is strong when-to-use guidance, though the description never names an alternative (e.g. check_fit for eligibility or search/list_products) or states when to avoid this tool entirely.

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