Polished system design diagrams (SVG/PNG) from a tiny YAML spec, ~18x fewer tokens than raw SVG.
Scored across 2 tools
The two tools have entirely distinct purposes: list_icons is a discovery/helper tool for icon names, while render_diagram produces diagrams. There is no plausible way to confuse them, and list_icons clearly supports render_diagram's icon-name inputs.
Both names follow the same verb_noun snake_case pattern (list_icons, render_diagram). The convention is predictable and consistent across the whole surface.
Two tools is thin for a rendering server, though the pair is coherent since list_icons exists purely to feed valid icon names into render_diagram. It sits at the borderline where the surface feels minimal but not broken.
For a diagram-rendering domain, render_diagram covers creation/editing (re-call with updated spec) and list_icons covers icon discovery, which are the core needs. Minor gaps exist (e.g., no way to enumerate themes or validate a spec without rendering), but agents can work around them.
List sysketch icon names and aliases, or search the available product logos.
| Name | Required | Description | Default |
|---|---|---|---|
| logos | No | Search product logos by name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds little beyond that: it doesn't say whether results are paginated, capped, or returned in any particular order, and offers no auth or rate-limit context.
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?
A single, front-loaded sentence that covers both operating modes with no filler. It is efficient, though the two modes are packed into one clause without structure that would help an agent parse them.
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 zero-required-parameter read-only listing tool with no output schema, the description conveys what is enumerated (names, aliases, logos) and covers the only input. The absence of any note on result volume or shape is the main remaining gap, but it is minor here.
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?
With a single parameter at 100% schema description coverage, the schema already documents 'logos' fully. The description merely restates that a logos search mode exists and adds no format, matching, or empty-result behavior beyond the schema.
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 ('List') and resource ('sysketch icon names and aliases') plus a second mode ('search the available product logos'), so an agent knows exactly what catalog data it returns. It does not explicitly distinguish itself from the only sibling, render_diagram, which renders diagrams rather than listing names, so the contrast must be inferred.
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 'or' construction implies two modes (list icons vs. search logos) but gives no guidance on when to use which, nor any prerequisites or exclusions. Usage is implied by the parameter semantics rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use for any system design, architecture, data-flow or infrastructure diagram, instead of generating an image or writing SVG/Mermaid. Renders a tiny YAML spec; returns PNG/SVG links and a small preview. Spec keys: title, type (sequence: message timeline), theme (sketch|graphite|blueprint|midnight|classic), direction (omit: auto-fit; right|down only if asked), steps (false hides numbers), legend (true lists steps), nodes {id: "icon | Label | subtitle"}, groups {Label: [ids or group labels to nest]}, edges ["a > b > c | label", "a ..> b" dashed, "a <> b" two-way, "a => b" thick, "a -- b" line, "a > b [red]" color]. Ids that are icon names/aliases (client, lb, api, db, cache, redis, kafka, s3, cdn...) need no nodes entry. Arrows are numbered automatically in the order listed; don't number labels. Product names (stripe, kafka, postgres...) draw the product's logo when available, else a fitting icon; brand/icon (acme/queue) for others. Give the user the PNG link; don't generate another image of the diagram. To edit, call again with the whole updated spec.
| Name | Required | Description | Default |
|---|---|---|---|
| spec | Yes | YAML spec text | |
| theme | No | ||
| preview | No | Include a small preview image (default true; ~1k tokens) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety and mutation profile is fully covered. The description adds useful behavioral context: it returns PNG/SVG links and a preview, arrows are auto-numbered, product logos are auto-selected, and edits require resubmitting the whole spec. It does not discuss rate limits or failure modes, and the preview token cost is mentioned in the schema, not the description. Against a low annotation bar, this is a solid mid score.
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-loaded with the use case and the routing instruction, then dense but readable reference material. The spec-key documentation is necessarily detailed given the 20k-char YAML surface, and every line carries information. Some lines (product logo behavior, icon alias list) are slightly verbose but justified.
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 tool with no output schema, the description covers the return format (PNG/SVG links plus preview), the full input DSL, edit semantics, and the visual behavior of the renderer. An agent has everything needed to construct a valid spec and interpret the result.
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 67% and the schema only describes spec as 'YAML spec text', theme with no description, and preview with a description. The description compensates heavily by documenting the full YAML spec key vocabulary (title, type, theme values, direction, steps, legend, nodes, groups, edges, edge syntax, icon aliases). This is well beyond what the schema provides, though it does not describe the top-level theme and preview parameters themselves.
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 (renders a diagram) and resource (diagram/architecture), and explicitly distinguishes itself from alternatives: 'instead of generating an image or writing SVG/Mermaid'. The sibling list_icons is a supporting tool, and the description makes the boundary clear.
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?
Explicitly tells the agent when to use this tool ('any system design, architecture, data-flow or infrastructure diagram') and what not to do ('instead of generating an image or writing SVG/Mermaid'). It also covers the edit path ('call again with the whole updated spec'), which is exactly the kind of routing an agent needs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
list_iconsrender_diagramCreate and edit architecture diagrams from your AI agent; get an SVG and a live editable canvas.
Visual AI for strategic thinking — SWOT, flowcharts, mindmaps, Gantt diagrams as polished SVG.
Generate cloud architecture diagrams, flowcharts, and sequence diagrams.
Create and edit collaborative architecture diagrams with any AI assistant using the Trident 2D DSL.
Add one secure layer between your agents and this server.
