ms_build_document

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

Annotations already provide readOnlyHint: true and openWorldHint: true. The description adds behavioral details: it resolves names to refs, shows the exact body, and notes money is in kopecks. It confirms read-only nature. No contradictions. Lacks description of error scenarios or potential behavior on failure, but overall transparent.

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 front-loaded with purpose and safety. Parameter documentation is thorough but somewhat verbose with nested lists. Could be slightly more concise, but structure is logical and easy to follow.

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 8 parameters, 2 required, 0% schema coverage, and an output schema present, the description is comprehensive. It explains all parameters, the return structure (including fields like resolved and summary), and even calls out specific behavior (auto-use organization, money in kopecks). No major gaps.

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 0%, so the description must compensate fully. It does: for each parameter it explains meaning (e.g., doc_type lists allowed values, agent defines counterparty role based on doc_type, organization auto-use, store requirement, positions format with fields and units, moment format). This adds essential context beyond the schema's type/title.

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 'PREVIEW any role document' and explains that it resolves names to refs and shows the exact body ms_create_document would send. It explicitly says 'READS only; no write', distinguishing it from sibling ms_create_document which creates. The verb and resource are specific and 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?

The description implies usage for previewing a document before creation via ms_create_document. It states 'READS only; no write' which guides when not to use (avoid if wanting to actually create). No explicit when-not-to-use or alternatives beyond the implied counterpart tool, but the context is clear enough.

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