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

Annotations only say this is a non-destructive, non-idempotent write; the description goes much further, explaining that nothing is created and no email is sent until the user clicks reviewUrl, that partner invitation emails are sent server-side on creation, and that the result reports delivery plus a shareable join link. That is exactly the side-effect detail an agent needs before invoking.

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 purpose and trigger are front-loaded and the bullets carry real operating rules, but the text is a dense wall that repeatedly restates the same prohibition on inventing prices and emails rather than stating it once. It reads partly as workflow coaching rather than tool contract, which lengthens scan time without adding new information.

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?

With 7 parameters, deep nesting, no output schema and no param descriptions in the schema, this is a complex tool — and the description covers the workflow, the reviewUrl handoff and the return behavior ('reports delivery and includes a join link'). The remaining gap is the un-narrated `fields` sub-object and its enums, though those are largely top-level metadata.

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 description coverage is only 29%, and the description compensates well for the semantic core — products-first with price/keywords/categories, holder 'me'/'open'/'partner' plus partnerRef, per-period pricing for recurring costs, and `why` on each row. But the entire `fields` object (track, vals, restime, currency, location, descripFor, linkToWebsite, publicDescription) and the cryptic `restime` enum are left unexplained, so a meaningful chunk of the payload is documented nowhere.

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?

The opening sentence states a specific verb and resource: turn a business/partnership/idea into a draft rikma containing products, missions, resources and partners. It also separates itself from the sibling `prepareForSomeoneElse` ('a rikma prepared for another person is prepareForSomeoneElse') and from creation tools ('Nothing exists ... until the person creates it there').

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?

Three concrete triggering situations are given ('add their business so the concierge can find and order from them', 'see how their partnership would look', 'break an idea down and recruit partners'), plus guidance on when to pass projectId and which sibling handles the prepared-for-someone-else case. There is no explicit 'do not use this for X' exclusion, so it stops short of 5.

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