dependency_parse

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

With no annotations, the description carries the full load and does well: it discloses the default engine per language, that Chinese is stanza-only and why (coarse spaCy zh labels, jieba cannot parse), and that stanza is also available for English. It omits any mention of max_sents truncation behavior or cost/latency, which are the remaining behavioral unknowns.

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 with the operation and output fields, then the language/engine constraints, which is the right order. The final clause ('far above keyword statistics') is promotional filler that does not help an agent act, costing a point.

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 values need no explanation, and engine/language guidance is solid. However, for a 4-parameter tool with zero schema documentation, the silent max_sents parameter (default 5, meaning silent truncation of longer text) is a real gap an agent could trip over, and no error or fallback behavior is described.

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% for four parameters, so the description must compensate. It adds real meaning for engine and lang (defaults, per-language availability, forbidden combinations) but says nothing about max_sents, the default of 5, or what values lang/engine accept and how 'auto' resolves — roughly half the parameters stay opaque.

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 first sentence names a specific verb (parse) and resource (dependency structure) and enumerates exactly what is returned per word: head, relation label, POS and morphological features. This distinguishes it unambiguously from tokenize, pos_tag, noun_phrases, and constituency_parse, since no sibling returns head/relation pairs.

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 explicitly positions itself as 'the entry point for syntax-aware extraction' with concrete example use cases (definitional clauses, subject/object probing, syntactic patterns) and contrasts itself with 'keyword statistics'. It still lacks an explicit routing statement against the closest sibling, constituency_parse, so an agent must infer which parse type to pick.

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