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

The description discloses a key behavioral trait not in annotations: the tool returns a Plotly spec JSON rather than rendering an image. It also describes two modes and chart type support, which helps an agent understand expected behavior. No annotation contradiction exists; annotations already mark the operation idempotent and non-destructive, and the description aligns with them.

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 description is dense but free of filler, and it front-loads the central purpose and return type. The long list of chart types is necessary but runs together without a table; a short structured breakdown would improve scannability. Overall it earns a 4 for economy and information density.

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?

Given 20 optional parameters and no schema-level descriptions, the tool description is not complete enough to invoke reliably across all supported types: it fails to define input conventions (column names vs raw values), the exact meaning of data_file, and per-chart required parameters. The existence of an output schema covers return values, so that absence isn't penalized, but input-side gaps remain significant.

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 0% schema description coverage, the description carries the full explanatory burden for 20 parameters, but it only clarifies the roles of a few fields (x/y/y2 for dual_axis, source/target/values for sankey, a/b/c for ternary, etc.). The general semantics of x, y, z, color, size, data, data_file, path, and title are left undefined, and the 'mappings' term in assisted mode is never spelled out. An agent would struggle to know which mapping fields to provide for basic charts like bar or scatter.

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 clear action and resource: 'Crée une visualisation Plotly (retourne le spec JSON)', immediately explaining what it does and its output. The two modes (spec libre vs assisté) and the enumeration of supported chart types further scope the tool. It does not explicitly contrast with sibling generate_map, but the Plotly chart focus and type list make it distinct.

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 clearly explains when to use each of the tool's own modes (free spec vs assisted chart_type+data+mappings) and lists supported chart types, giving an implicit range of use cases. However, it gives no explicit when-not-to-use guidance or alternative sibling tools (e.g., generate_map for maps). The usage context is conveyed but not contrasted with alternatives.

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