Render a drawspec document to SVG, PNG or text

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

With no annotations, the description carries the full burden and does well: it discloses the inline-paste safety properties (no global styles, no colliding ids, no colour-only meaning), the optional `drawspec[png]` server extra required for PNG, and the failure mode (refuses with located violations like validate). It stops short of stating idempotence/read-only nature or any cost/size limits on large renders.

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?

Front-loads the default behavior ('return the SVG') and the safety guarantee before covering the png/text variants and error behavior. Every clause earns its place; the png parenthetical is dense but necessary information, not padding.

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 an 8-parameter tool with a nested `document` object, no output schema and no annotations, the description covers output formats, the external schema URL for the document shape, safety characteristics, and error behavior. It leaves the actual return payload structure (what the SVG response object looks like) unstated, which is the main remaining gap.

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 100%, so every parameter including scale, theme, width, height, charset, background and format is already documented in the schema. The description only reinforces the format branches and the png extra requirement, adding no syntax or format detail beyond structured fields, which matches the baseline 3.

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 ('Draw the document and return the SVG') and immediately enumerates the three output modes with their formats. It also positions itself against a sibling by noting it refuses with violations 'exactly as `validate` does', so an agent can tell render apart from validate/kinds without opening schemas.

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 clear context for each format branch: png 'for a chat, a slide or an attachment', text 'for a code block or a terminal'. However it never explicitly says when to call this instead of validate (e.g. 'call validate first if you want errors without output'), so the routing against the primary sibling is only implied.

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