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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds useful context: source (DILA LEGI base) and the status vocabulary (VIGUEUR, MODIFIE, ABROGE). It also notes the 20-most-recent-versions cap for text. It omits error behavior and what happens when neither retrieval path is valid.

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 core definition, then invocation guidance, then intent examples. Every sentence carries information with no filler.

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?

No output schema exists, and the description compensates by listing the per-version fields returned. The remaining gap is that no parameter is required (required: 0), yet the description never states that one of the two retrieval paths must be supplied.

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 100%, so the baseline is 3; the description adds meaning by framing `id` versus `code`+`article` as alternative retrieval paths and noting `id` can be any version. It doesn't add format detail beyond the schema examples.

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?

A specific verb and resource: 'Version history of an article of a French code', with the returned fields enumerated (entry into force/end dates, status, text). It is clearly distinguishable from siblings like fr_code_article (single article lookup) and fr_legi_search by its focus on the full version timeline.

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?

Gives concrete 'use for' examples ('how has article L1237-19 changed', 'what did article 1382 say before 2016') that tell an agent exactly the intent it serves. It does not explicitly name an alternative tool or state when-not-to-use, so it stops short of a 5.

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