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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond them: it enumerates what comes back (real SVG, hashes, accessible output, normalized spec, certification) in the absence of an output schema, and pins the input channel to inline data. It stops short of mentioning failure codes or certification gating.

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?

Three short sentences, front-loaded with the verb. The final clause restating brand/theme enums is mild redundancy against the schema, but the whole thing is tight and wastes little space for a tool of this complexity.

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?

For a 19-parameter tool with 13 chart types and no output schema, naming the returned artifacts is a useful addition. But the description omits the overarching mode model (pattern vs chartType+encodings vs rows/intent), which is the single most important routing decision an agent faces; that information lives only in the schema. Adequate but not complete.

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 84%, so the schema already documents parameters thoroughly (chartType, geo, hierarchy, encodings, pattern, strictFields all carry rich prose). The description only restates the brand and theme enum values ('brands A/B and light/dark/hc'), adding no semantics beyond the structured fields. Baseline 3 is appropriate.

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?

States a specific verb+resource ('Draw a chart') and the delivery mechanism ('through this site's chart route'), which is concrete enough to distinguish it from sibling tools like artifact_certify. It does not explicitly contrast with siblings, but none of them plausibly collide with rendering a chart.

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?

'Inline data only' gives one real boundary condition (no remote/network data), and the return-content sentence implies it is the rendering step. However, it never says when to reach for this tool versus alternatives such as design_preview, nor does it route between the pattern / chartType / structured-intent modes that dominate the schema.

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