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

Annotations already declare read-only, open-world, non-destructive, non-idempotent, but the description adds real context: the rendering host (Darwin/AntV), that the output is a PNG image, row and size bounds, and that no API key or payment is involved. It stops short of disclosing latency, rate limits, or failure behavior.

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 purpose and selection rationale are front-loaded, with operational constraints packed efficiently afterward. The clause about eyes judging height is wordy but earns its place by justifying tool choice over alternatives.

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?

Hosting, auth, output type, and limits are covered, and the output schema means return values need no explanation. But for a 10-parameter tool with nested style and a mutually exclusive group/stack pair, the description provides no parameter-level guidance to supplement the thin schema coverage.

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 only 30% across 10 parameters, so the description must compensate and largely does not. It only restates limits already in the schema (50-row maximum, bounded image sizes) and says nothing about group/stack interplay, the nested style object, palette, theme, or axis titles.

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 and resource ("Generate a column chart") and adds a usage rationale about comparing categorical data, which implicitly separates it from the line-chart sibling. It never names generate_bar_chart, so the column-vs-bar distinction an agent most needs is left implicit.

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 a clear when-to-use condition: comparing categorical data, especially when values are close, because height is easier to judge than area or angles. There is no explicit when-not or named alternative, so an agent still has to infer bar vs. column vs. line selection.

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