text_normalized

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

With only readOnlyHint available, the description carries real behavioral weight: it enumerates the exact normalisations applied (NFC, soft-hyphen/zero-width removal, whitespace collapsing) and discloses the offset-map contract that maps normalised to original code points. It stops short of describing limits, cursor paging behavior, or error cases, so not a full 5.

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?

Front-loaded and dense: the core operation and dominant output artifact appear first, and the sentence is packed without filler. It is slightly run-on and would read better split, but every clause earns its place.

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?

There is no output schema, but the input schema's top-level description thoroughly covers the return shape (paragraphs, start/from/text/offset_map, part-of-parts, run encoding), and the tool description states the normalisation semantics. Together they are sufficient for correct invocation of a moderately complex read tool, with only paging/limits nuance arguably thin.

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 100%, so the schema already documents every parameter (`at`, `doc`, `text`, `limit`, `cursor`) including the range syntax and the ~8,000-byte cap. The description only restates the doc-vs-text modes and adds no syntax or format meaning beyond what the schema provides, so the baseline 3 is correct.

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 transformation (NFC normalisation, removal of soft hyphens/zero-width chars, whitespace collapsing) plus a return artifact (two-way offset map), and names the two input modes (document or text string). It clearly says what the tool produces, though it never names or contrasts a sibling such as segment or diff, leaving sibling differentiation to inference.

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 by explaining the two operating modes ('for a document (whole, or the paragraph/range `at`) or for a `text` string'), which tells the agent which input to reach for. However, it gives no explicit when-to-use/when-not guidance and never points to an alternative tool, so it stays at implied rather than stated guidance.

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