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

Beyond the read-only and idempotent annotations, it discloses single-article filtering, entry contents, clause preview behavior through lead_text and text_chars, and the scale of large acts. It does not explain truncation or how the default result limit interacts with the advice not to paginate.

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?

Three compact paragraphs front-load the purpose and resolver example, then cover output structure and large-document usage. The wording is dense but every sentence supplies actionable 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?

For a six-parameter read tool without an output schema, it covers ordering, important returned fields, article lookup, downstream URN usage, and a strategy for large documents. The main remaining gaps are how to obtain nreg and precise limit, truncation, and paging behavior.

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?

The description adds meaningful semantics beyond the schema by showing how kind and number combine to resolve one article. Its filtering advice also contextualizes limit and offset, although those two schema-undescribed parameters and their truncation behavior remain unexplained.

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 identifies the resource and result ordering—one document's units in reading order—and also defines an exact article-resolution mode. "Structure only" and the reference to get_unit_fulltext distinguish it from full-text retrieval siblings.

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?

It gives an executable example using kind='article' and number='626', explains how returned URNs feed get_unit_fulltext, and explicitly advises "Filter, do not page." These details provide concrete guidance on both invocation and the downstream workflow.

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