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

With destructiveHint=true already declared, the description adds real context: exactly one offer is kept per product and it can be changed at any time, which tells the agent a write replaces the single stored value rather than appending. 'Free.' also discloses that configuring costs nothing. It does not say what happens to fields belonging to a previously chosen kind.

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?

Everything is packed into one long run-on sentence with nested parentheticals, which makes the kind-to-field mapping hard to scan. The content is mostly load-bearing, but the structure works against quick comprehension and 'Free.' is an unanchored fragment.

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 six-parameter, mutation-capable config tool with no output schema, the description covers what is stored and how it is scoped. The gap is the read path: 'reads it' never says what is returned when kind is omitted, and there is no output schema to fill that in.

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 schema already documents every parameter, and the baseline is 3. The description does add modest value by pairing each kind with its fields ('call ... with their booking link', 'credits (amount, in unit ... to at most cap people)'), but the same mapping is already legible from the per-property descriptions.

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 the resource concretely: the offer placed in each follow-up note to a stuck signup, kept once per product and editable. It enumerates the five offer kinds (call, setup, question, credits, own) so the agent grasps the domain, but never names a verb like 'set/read' up front and never distinguishes itself from siblings such as offer_plan or followup_targets.

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 clause 'Without kind, reads it' is a genuine usage rule that tells the agent the tool is dual-mode (read when kind omitted, write when kind supplied). Beyond that there is no guidance on when to reach for this versus offer_plan or followup_targets, and no prerequisites or sequencing hints.

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