TikZ 그림 렌더링

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

Annotations only declare readOnlyHint=false, openWorldHint=false, destructiveHint=false; the description adds real context beyond that — supported output formats, a returned preview image, auto-wrapping of bare \draw commands, and a precise error contract ('! line' plus 'l.N' = line N of your code). The phrase 'mostly automatic' for packages/libraries/labels is left vague, and it never says where generated files land despite readOnlyHint=false implying artifact creation.

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?

Purpose is front-loaded, then domains, a runnable inline example, a verification checklist, and a failure-recovery rule — a sensible order with no filler sentences. It is dense but every block maps to a decision the agent must make; the only slack is the compressed 'mostly automatic' clause.

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 4-parameter tool with no output schema, the description covers what comes back (preview image plus SVG/PDF/PNG), how to prepare input (get_template), and how to recover from compile errors. The remaining gap is artifact lifecycle: with readOnlyHint=false and a `name` parameter, an agent still cannot tell where the compiled files are stored or whether export_document is needed to retrieve them.

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, and most of the description's parameter-relevant content ('packages, libraries ... mostly automatic') merely restates the schema's own 'usually auto-detected' notes. The one genuine addition is that bare \draw commands get wrapped, which expands what the agent knows it may pass as `code` — useful, but thin overall.

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 first sentence gives a concrete verb and resource ('Compile TikZ/circuitikz/pgfplots/chemfig code into a figure') plus concrete output formats and the returned artifact (preview image). The following sentence ('For circuits, free-body diagrams, vectors, geometry, block diagrams') implicitly separates it from plotting siblings like plot_function/plot_data, but it never names those alternatives, so the differentiation is by inference rather than explicit.

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?

'Adapt a similar example from get_template first' gives an explicit prerequisite workflow naming a real sibling tool, and the closing line tells the agent what to do after failure ('fix it and call again'). What is missing is a negative rule: no statement of when NOT to use this (e.g. use plot_function for function graphs, render_molecule for structures), which is the main ambiguity against this sibling set.

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