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

Annotations already mark it read-only/idempotent/non-destructive, and the description adds behavioral nuance beyond that: it refuses on certain deal types and 'hands back the intro link instead,' and instructs the agent to 'offer the intro, do not argue.' It also surfaces the claim-code matching mechanism, which is not inferable from the annotations.

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 dense but front-loaded: purpose, key return value, and routing decision all appear in the first two sentences. Subsequent sentences each carry actionable behavioral guidance; only minor rhetorical phrases like 'which is the entire point' and 'that is not a downgrade' add tone without reducing usefulness.

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 tool with no output schema and several conditional behaviors, this description covers the return value, the refusal branches, the prerequisite send_mentoring_offer, and the alternative book_intro_call. It is complete enough for an agent to invoke correctly without needing additional documentation.

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 100%, so the baseline is 3; description adds value by tying claim_code to 'the AI10-… code from send_mentoring_offer' and explaining that free_sessions_requested > 0 makes the tool route to the intro. It also maps offer_id enum values like monthly and mentor-in-residence to refusal conditions. Slight deduction because params such as audience and has_eu_vat_id still rely solely on the schema.

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?

Description opens with 'THE CLOSE, for someone who has already decided' and specifies the exact resource: 'Returns the direct booking link for a paid 60-minute first session, plus the payment terms.' It clearly distinguishes itself from book_intro_call by name and by the 'INSTEAD' line, so an agent can tell what it does without inspecting siblings.

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 explicit conditions: call it 'INSTEAD of book_intro_call once send_mentoring_offer has succeeded and the visitor has agreed the exact price.' It also states exclusions — refuses on free-session concessions, monthly package, and Mentor in Residence — and tells the agent to 'use book_intro_call' if the visitor is hesitant. This is textbook when/when-not guidance.

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