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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: output lines are numbered, long files continue via a returned line_offset, and theme files carry a revision. It stops short of describing error conditions (missing path, unknown draft ref) or the default line limit.

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?

A single dense paragraph that front-loads the core action and then packs in the readable file kinds, pagination behavior, and the #info trick with no filler sentences. The embedded query example is slightly awkward inline but earns its space as actionable guidance.

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, so the description carries the return-value burden, and it does so adequately by explaining line numbering, line_offset continuation, and revision metadata. For a 6-parameter read tool with full annotation coverage, the remaining gap (error behavior, default and maximum line counts) 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?

With 100% schema description coverage, the schema already documents path, draft, store, line_limit, char_offset, and line_offset, so the baseline is 3. The description reinforces the path domain (theme files vs. .entities documents) and ties line_offset to its source ("from a previous read"), but adds no format or default guidance for line_limit or char_offset.

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 names a specific verb and resource ("Read a file in a Fudge draft") and then enumerates the three readable shapes: theme file, theme folder listing, and content document under .entities. That is enough for an agent to distinguish it from delete_draft_file, edit_draft_file, and write_draft_file without opening a schema. Differentiation from the non-draft read siblings (read_store_document, read_work) is not addressed.

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?

Useful in-tool guidance is given: how to enumerate content documents ("list with .entities/product?query=…") and the "#info" suffix to see where a theme file is used. However, there is no explicit statement of when to pick this over read_store_document, read_guide, or search_draft_files, so the choice among read siblings 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.