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

Annotations declare a non-read-only, open-world, non-destructive write, and the description adds real context beyond that: the lead is submitted to an external party, an email is sent to the user unless test=true, and test leads are marked TEST. It stops short of describing the success response or failure modes, but the consent gate and email side effect are the critical disclosures and they are present.

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-loads the identity and purpose in one sentence, then uses a numbered precondition list that an agent can follow step by step. Every sentence carries actionable content, with no filler or repetition of the title.

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 external submission tool with no output schema, the description covers the consent gate, data-provenance rules, and test-mode behavior, which are the highest-risk aspects. What remains unstated is what a successful submission returns or how errors surface, a modest gap given no output schema exists.

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 the schema documents most parameters. The description still adds meaning the schema does not: consent must be set only after explicit user agreement, test implies no customer email, and task_summary/proposal should originate from prior tool calls. It does not clarify ref, phone, or mcp_client intent, which the schema handles only thinly for phone.

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?

States a specific action (submit a Free First Task lead to The Outcome Layer), identifies itself explicitly as an alias for request_free_first_task, and notes the equivalent human channel (the website form). This differentiates it from siblings like get_proposal or build_handoff_link, which produce artifacts rather than submit them.

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 unusually explicit preconditions: obtain consent, collect real contact data, and include task_summary and/or proposal from prior tools before calling. It also explains test=true for dry runs. The one gap is that it never says when to pick send_to_tol over the sibling request_free_first_task, leaving an agent to guess which alias to invoke.

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