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

No annotations are provided, so the description carries the full burden. It explains the chapter semantics mapping and notes that it reads by paragraph range, but doesn't disclose behavior like whether reads are cost-free, pagination limits, or what happens with out-of-range paragraph numbers. Given the field scope covered (setting expectations for chapter vs paragraph semantics), a 4 is generous but reasonable.

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 compact—two sentences plus a work listing. The work enumeration takes space but is genuinely necessary since there's no enum in the schema. The usage directive is folded efficiently into the second sentence. Could be slightly more concise in the work list but it serves a real purpose.

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 an output schema present, the return format isn't the description's job. Given 4 params at 0% schema coverage and no annotations, the description covers the most critical ambiguity (work enumeration and chapter semantics) and points to search and corpus_info as discovery aids. The start/end paragraph range semantics remain slightly under-specified, keeping it at 4.

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 description coverage is 0%, so the description must compensate for all 4 params (work, chapter, start, end). The description clarifies work (lists valid values and how to discover them) and chapter (mapping to book chapters). However, start and end paragraph semantics are implied but not fully spelled out (e.g., whether end is exclusive), so it falls short of 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?

The description clearly states the verb+resource: 'Read a prose work from the corpus by paragraph range.' It names all 8 available works, distinguishing it from the 11 sibling tools (search, get_passage, etc.) which serve different purposes (searching, comparing, citation retrieval).

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 explicitly guides when to use this tool vs alternatives: 'use search(version=<WORK>) to find passages first, or corpus_info() for the full list.' It also clarifies the chapter semantics ('Chapters = books/chapters of the work'), directly addressing a likely source of confusion and providing actionable next steps.

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