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

With zero annotations, the description carries the full burden and does it well: it discloses the ~24k character truncation limit, the exact resumption mechanism (paragraph = next_paragraph), the accent- and breathing-insensitive matching semantics with examples, and the shape of each return (TOC with paragraph counts; original/translation row by row with section and paragraph locators). There is no contradiction and no significant undisclosed behavior.

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 mode structure is front-loaded ('Without a section... With a section... With find...') and each clause maps to a parameter-driven behavior, so little is wasted. The sentences are dense and long, and the pagination detail is buried mid-sentence rather than given its own line, which slightly hurts scannability.

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 4-parameter, no-annotation, no-output-schema read tool, an agent has everything needed to invoke it: what each mode returns, the size cap, the continuation path, and match semantics. Only the id format remains unspecified, which is minor.

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 only 50% (id and section are undocumented in the schema), and the description compensates well: it explains what section does with and without, what paragraph means (start/next read point), and richly characterizes find (any language, accent/breathing-insensitive) with sample queries. The id parameter's expected format is still never stated in either place.

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?

States a specific verb and resource ('Read a work from the shelf') and then enumerates the three distinct behaviors keyed off section/find, so the agent knows exactly what comes back in each mode. It never differentiates itself from siblings like get_passage or search_shelf, which have obvious overlap, so it falls short of a 5.

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?

Gives explicit mode-selection guidance: no section → table of contents, section → text, find → search. It even handles the continuation case ('if truncated, call again with paragraph = next_paragraph'), which is real when-to-use instruction. However it gives no guidance on when to prefer this over search_shelf or get_passage, so cross-tool routing is left to inference.

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