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

Annotations only say readOnly=false, destructive=true, openWorld=true; the description adds the real behavioral burden: giving a discount sends a one-time customer email, ending one emails the customer that it ended, `customerEmailed` reports whether it truly went out, `note` is never customer-visible, and the checkout/billing consequences (months charged up front, then normal monthly price resumes, Razorpay INR and PayPal USD). This is well beyond what the annotations declare.

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 with the OPERATOR ONLY constraint and scoped in the first clause, with no filler sentences. However, it is a single dense block of long sentences that mixes modes, refusals and return fields together, so it is harder to scan than a shorter or segmented version would be.

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 9-parameter, zero-required, mutation-heavy tool with no output schema, the description covers naming the team, all three discount kinds, the deadline, refusals, the email side effects, and even the returned `adminSentence` and `customerEmailed` fields. Nothing an agent needs to invoke it correctly is missing.

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, but the description genuinely adds meaning: `amount` is a fixed per-month figure in the team's billing currency in major units (with a ₹500 example), `validUntil` is good to end of day UTC and capped at a year ahead (a limit absent from the schema), and the three team-naming options plus the refusal when `account` is ambiguous. Some of this does restate schema enum text, keeping it below a 5.

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 verb set (read/give/end) on a specific resource (a customer team's discount on a new subscription) and immediately scopes it as operator-only. It also disambiguates from siblings by name: li_set_trial_end_offer is called out as the tool for the post-trial automatic offer, and the billing/complimentary siblings are implicitly separated by the 'new subscription only' constraint.

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?

Explicit when-to-use for each mode: omit kind/end to read, supply kind to give, use end:true to terminate. Alternatives and refusals are enumerated (already-paying teams, free/complimentary teams, teams with a running discount), and the reader is routed to li_set_trial_end_offer for the different scenario.

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