Parse free-form text

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

With no annotations supplied, the description carries the full burden and does so thoroughly: a parse failure on an existing file returns a non-raising ValidateResult (valid=False, single errors[].message capped at 300 chars) instead of raising AssertionError/ValidationError/YAMLError, while an absent or unreadable path still raises FileNotFoundError/PermissionError/OSError from Path.read_text(). It also discloses the language-table resolution rule and the actionable ValueError when a table is missing.

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?

Core purpose is front-loaded, which is good, but the body is a single dense run-on with embedded ADR UUIDs (f14f125e..., 519d1206) and issue/feature tags (feat-110, #204) that add little for an agent selecting the tool. The substantive behavioral content earns its place; the internal tracker references do not.

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?

An output schema exists, so return-shape explanation is optional, yet the definition still covers the important success/failure split and language resolution for a tool with non-trivial error paths. Minor omissions (encoding assumptions, whether it writes anything back to disk) keep it short of a 5.

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 0%, so the description must supply the meaning of 'path' — and it does, explaining that the file's language is derived from its position relative to the free-form text base directory (flat docs/txt/ = canonical, docs/txt/{language}/ = table-mapped, anything else = canonical). It never states explicitly whether an absolute path is accepted, which is the remaining gap.

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?

Opens with a specific verb and resource: 'Parse a free-form text markdown file (YAML frontmatter + body) from disk into a structured ... TxtDocument'. This clearly separates it from the read-only get_txt/list_txt siblings and from the other parse_* tools that target different document types.

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 purpose implies when to use it (you need a structured object from a .txt file on disk rather than raw content), but there is no explicit statement of when to prefer get_txt, get_txt_schema, or validate instead. Guidance is inferred rather than stated.

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