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

Annotations only cover readOnly=false, openWorld=true, destructive=false; the description adds genuinely new behavior: an external customer-facing lead is created, a confirmation email may reach the user, and test=true suppresses that email and flags the lead TEST. It stops short of saying what happens on duplicates, retries, or what a successful submission returns.

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?

Front-loaded one-line purpose, then a numbered precondition block, then two short directives for the consent and test flags. Every line carries an instruction an agent must follow; nothing is redundant.

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 10-parameter, nested-object, open-world submission tool with no output schema, the description covers the critical preconditions and the test escape hatch. It could still say what the tool returns (lead id, confirmation) and what to do on failure, which matters given there is no output schema.

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 coverage is already 90%, so baseline would be 3, but the description adds real semantics: consent must be true only after explicit user agreement, test means no customer email, and name/email/company must originate from the user rather than being invented. It says less about ref, mcp_client, and phone, which rely on 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?

Specific verb + resource: submits a Free First Task lead to The Outcome Layer, and the parenthetical '(same as the website form)' clarifies what the record actually is. It does not, however, differentiate itself from the sibling send_to_tol, which an agent could easily confuse with this tool.

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?

Gives an explicit precondition checklist (consent, collect real contact data, include task_summary/proposal) plus a dry-run path via test=true. What it lacks is routing guidance against the similarly named send_to_tol sibling, so the agent must guess which submission tool applies.

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