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

With no annotations, the description carries the full burden and does well: it discloses that no server key buys for anyone, that it returns an approval page for the human's passkey, that only devnet test money is involved, and that it requires human confirmation. What happens after approval, and reversibility/timing, are not covered.

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 purpose ('Prepares a pre-order of an OPEN report'), then the confirm-first safety warning, then the parameter note. Dense but each sentence earns its place; no filler.

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 mutation tool with zero annotations and no output schema, the description covers the safety profile, the human-in-the-loop requirement, the funding type, and the session dependency. The remaining gap is identifying what 'report'/'units' mean, which is left to the agent to infer.

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 0%, so the description must compensate. It explains 'session' (the token from knos_sign_in) but leaves 'report' and 'units' unaddressed beyond their names, so only one of three parameters gets real semantics. Partial compensation is worth a 3, not more.

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+resource on a specific class of object: 'Prepares a pre-order of an OPEN report' and clarifies that it returns an approval page rather than executing a purchase. The passkey-approval flow (vs. a server-side buy) distinguishes it from generic purchase siblings. It could be sharper about what a 'report' identifier is, but the purpose is unambiguous.

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 'CONFIRM FIRST' instruction to ask the human before calling, plus a dependency: pass the session token that knos_sign_in returned. This gives clear context and a precondition. It stops short of naming competing siblings or when-not-to-use conditions, so not a 5.

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