Read passages by URN

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

Annotations only declare readOnlyHint, so the description carries the rest and does so richly: truncation is "honest" and bounded by max_passages (default 50, cap 200), withdrawn/retired items are surfaced and flagged, license_class and urn ride along and must be preserved, meter/findspot keys are present-only with an explicit caveat that absence is absence of enrichment rather than absence of fact. The include_restricted note warns that this surface must never casually leak private material.

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 key routing information (urn shapes) is front-loaded, but the single dense paragraph runs long, mixing urn grammar, output-field semantics, and per-flag behavior in one block. Several sentences restate the input-schema descriptions for `senses`, `segmented`, and `max_passages` nearly verbatim, so the text does not fully earn its length.

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 7-parameter, output-schema-less reader, the description covers the urn grammar, all opt-in flags with their fallback notes, pagination bounds, and the shape of returned records (urn, language, license_class, notes, meter, findspot, senses). Nothing an agent needs to call it correctly or interpret the payload 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?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema: concrete urn examples per grain, `parallel_lang` defaulting to eng for the same work's edition line by line, and what `senses`/`segmented` return when applicable versus the `senses_note`/`segmentation_note` fallback. The overlap with schema text (senses, segmented, max_passages) is largely redundant, which keeps it from a 5.

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?

"Read the nabu corpus by urn" gives a specific verb plus resource, then enumerates the exact urn grains it accepts (passage, document, inclusive range, papyrus, treebank sentence, citation prefix). The "term-less browsing needs no search hit first" clause implicitly separates it from nabu_search.

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?

Usage context is clear: it is the direct-read path when you already hold a urn or want to browse an entire citation subtree without a search hit, and include_restricted carries an explicit "set true only when the requester understands and will honor the restriction" gate. It never explicitly says when to prefer a sibling such as nabu_search or nabu_parallels, and the `parallel: true` flag is not differentiated from the nabu_parallels tool.

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