List free-form text documents

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

With no annotations provided, the description carries the full burden and does so well: it discloses paging defaults (25, capped at 100), that out-of-range values are clamped rather than errored, that invalid-shaped language codes raise ValueError before any file access, and that a shape-valid language lacking a heading-mapping table is rejected up front. It doesn't explain sorting order or what 'statuses' actually mean, which keeps it just shy of a 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?

The listing behavior is front-loaded and most sentences earn their place, but the language sentence is dense and repeats itself ('omitted/'en' = the flat docs/txt/ directory (the default behavior, unchanged)'). The parenthetical redundancies and nested clauses make it slower to parse than necessary.

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-value documentation is correctly omitted, and the description covers everything else the agent needs for a filtered, paginated, language-scoped list: filtering semantics, paging limits, error conditions, and the ref-handoff to get_txt. Nothing material is missing for correct invocation.

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 entirely, and it does: glob is case-insensitive against ids with an example ('dead*'), None lists everything, and empty string matches nothing; max_results/offset have defaults, caps, and clamping semantics; language has a default, an ISO 639-1 shape constraint, and a precise directory-mapping rule. This is meaning the schema cannot convey on its own.

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 opens with a specific verb and resource ('Ids, titles, statuses, and refs of free-form text documents in the configured free-form text base directory') and immediately distinguishes itself from the sibling get_txt, which retrieves a single document by id. An agent can tell list_txt apart from get_txt, list_languages, and the other list_* siblings without opening any schema.

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?

It states the intended use case ('for context before addressing one by id') and names the alternative explicitly: opaque 'ref' values must be passed to get_txt rather than treated as filenames. It also covers the default behavior (glob=None lists everything) and the deliberate absence of an 'all languages' mode, leaving little to infer.

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