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

With no annotations, the description carries the full behavioral burden and does so richly. It discloses that the tool validates and returns a summary/consent line/token, that a second call is required, that the person must receive and click an email link before any provider sees the enquiry, and exactly what consent means. This is far beyond the minimal mutation indication.

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?

The description is long but every sentence earns its place given the two-step stateful flow. It front-loads the core action and the most important caveat ('NOT a purchase'), then lays out step 1, step 2, and the consent requirement without redundancy. The quoted consent text is necessary because it is the exact semantic contract for the consent parameter.

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?

This is a high-complexity tool: two-step submission, human involvement, consent requirements, and an email confirmation link. The description covers all of it, including what the agent must show the person and when the second call is permitted. With no annotations and no output schema, the description is complete enough for an agent to invoke the tool correctly.

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 100%, so the baseline is 3, and the description adds meaningful context: answers must be keyed by field keys from enquiry_fields, consent maps to an exact quoted agreement, and confirmation is the token returned from step 1. This enriches the bare schema definitions and clarifies the relationship between the two required/optional parameters.

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 states a specific action ('submits an enquiry'), names the resource (SR&ED Claim Calculator / human providers), and clarifies the two-step nature. It also explicitly distinguishes itself from a purchase or guaranteed quote, which prevents a common misinterpretation and separates it conceptually from sibling calculator tools.

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 description gives explicit step-by-step usage: Step 1 with answers and consent=true, then Step 2 with the confirmation token only after the person agrees. It also tells the agent to show the summary and consent line to the person. It does not explicitly name alternative tools like 'calculate' for when-not-to-use, but the 'NOT a purchase' warning and reference to enquiry_fields provide helpful boundaries.

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