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

Annotations already declare readOnly/openWorld/no-destructive, and the description adds substantial behavior beyond them: worst-permissible-fill is checked against the equity's Chainlink total-return mark and refused when over tolerance or when the feed is frozen (>24h), the pair is returned unchanged plus a preview, and nothing is signed or submitted. It also discloses the 300-second envelope validity window and that stale envelopes are refused by the verifier.

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 core purpose and organizes the many constraints (fill check, refusal conditions, no signing, delegation retirement, 300s TTL) in a single dense paragraph. Every sentence carries information, though the density borders on a wall of text that could be split for faster scanning.

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 preparation tool with an output schema already documenting return values, the description still covers the important operational facts: authorization status, timing (valid_until), refusal conditions (fill over tolerance, frozen feed), and non-custodial behavior (never signs/submits). Nothing essential to correct invocation 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?

With 50% schema coverage, the description compensates for the undocumented fields: executableEquityId is explained as naming the registry row and never being an input, and registryCommitment is clarified as having to equal the value recomputed over the CURRENT record (stale/foreign rows refused by name). client_ref and accountProfile remain unaddressed in both schema and description, leaving a modest gap.

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 precise verb+resource: it prepares the exact otto_prepare_swap pair (envelope + prepareInput) that buys one of the executable Coinbase B20 tokenized equities on Base with USDC. It explicitly contrasts with the generic otto_prepare_swap sibling and names the exact scope (B20 on Base only), so an agent can distinguish it without opening schemas.

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 clear context for use: buying tokenized equities where the equity comes from a registry row rather than as an input, and notes the related otto_submit_under_delegation path refuses this pair and delegated trading is retired. It never states an explicit when-to-use-this-vs-otto_prepare_swap exclusion, but context is strong enough to route correctly.

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