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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description goes well beyond those annotations by explaining token lifetime, placeholder-token invalidity, preview-and-confirm flow, preflight-not-confirmation, and counterparty-explicit confirmation scope. This is high-value behavioral context. There is no contradiction between description and annotations, so behavioral transparency is strong.

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 description is a compact paragraph that front-loads the core action, then covers the token, preview, and confirmation rules without redundancy. It packs a lot of information into a dense block but each sentence contributes important constraints. A slightly more structured layout might help, but it is appropriately sized and not padded.

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 destructive, high-stakes transactional tool with no output schema, the description covers the confirmation protocol, token lifetime, and batch limit. It does not explicitly mention connectionRef reuse or CR analysis category confirmation, but those are documented in the schema. It also does not describe return values beyond confirmation_required and payload preview, which is sufficient because no output schema exists but the key response behavior is stated. Overall it is complete enough for an agent to call correctly.

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 including the elaborate nested quote structures. The description adds semantics for routeToken, confirmWrite, and confirmCounterpartyExplicit—namely token validity, preview-before-confirm, and explicit counterparty confirmation—which are not fully captured by the schema descriptions. It does not describe every nested field, but the schema carries that load. Given 100% coverage and rich schema descriptions, a 4 is appropriate since the description adds the operational semantics.

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 description clearly states the tool processes a batch of quotes via two payload forms and sets the 20-item limit, so the verb and resource are specific enough to distinguish it from single-quote create tools and other batch tools. It doesn't explicitly name a sibling like brc_create_quote, but the batch name and scope are evident.

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 description strongly implies when to use this tool with routeToken requirements, the need for confirmWrite true and confirmCounterpartyExplicit true, and the fact that preflight is not confirmation. It even warns placeholder tokens are invalid and describes the confirmation flow, effectively guiding the agent through the correct call sequence. It doesn't name alternative tools explicitly, but the workflow rules are otherwise explicit. Since explicit when/when-not guidance is present through the confirmation-flow rules, this earns a 5.

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