Visualisation graphique

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

Annotations indicate readOnlyHint=false (non-read-only), destructiveHint=false, idempotentHint=true. The description accurately portrays the tool as creating a visualization and returning a JSON spec, which is non-destructive and idempotent. It adds context about the output format not in annotations.

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 concise with two short paragraphs and a bullet list. Every sentence adds value, front-loading the purpose and modes. No unnecessary words.

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?

The tool has 8 parameters and no required ones. The description covers the two modes and some params, but misses color, title, and data_file. An output schema exists, so return format is covered, but input documentation is incomplete, making it less than fully helpful.

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 description carries the burden. It explains the two modes involving spec, chart_type, data, x, y. However, it omits parameters like color, title, and data_file, leaving them undefined. This partial coverage is insufficient given the 0% schema coverage.

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 clearly states 'Crée une visualisation Plotly (retourne le spec JSON)' with specific verb and resource. It lists two modes and supported chart types, distinguishing it from sibling tools focused on data queries/export.

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 description explains when to use each mode (free spec vs assisted) and lists supported chart types. It does not explicitly state when not to use the tool or name alternatives, but the context is clear enough for most cases.

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