preview_diagram

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

Annotations declare readOnlyHint=false, openWorldHint=true and destructiveHint=false, so safety is partly covered. The description usefully adds that the tool opens a browser window (an observable side effect consistent with openWorldHint) and that source display is optional, which is real context. It stops short of saying whether a browser window is spawned on every call, whether the page persists, or any auth/environment requirements.

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, purpose front-loaded, with no padding. The middle sentence lists features that are largely already enumerated in the schema, which is mild redundancy, so it is efficient but not flawless.

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 preview tool with no output schema and full schema coverage, the description covers what the tool does and the browser-based output. It leaves unaddressed whether diagrams render inline, how multiple diagrams are laid out, and how the browser preview is surfaced to the agent, so it is nearly but not fully 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 100%, so the schema already documents theme, palette, diagrams, include_source and the nested dgmo/title fields, making the baseline a 3. The description's mention of 'theme toggle and optional source display' loosely maps to two parameters but adds no formatting or override semantics beyond what the schema states; palette is not mentioned at all.

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?

Names a specific verb+resource ('Render one or more DGMO diagrams and open an HTML preview in the browser'), which is concrete and actionable. It does not, however, distinguish itself from the sibling render_diagram, which an agent must infer from the 'HTML preview' phrasing. Without that explicit sibling contrast, it stops short of a 5.

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 only routing guidance is 'For DGMO syntax call get_language_reference', which points at a supporting tool rather than saying when to choose preview_diagram over render_diagram or share_diagram. Usage is only implied by the phrase 'preview'. No when-not conditions or alternatives are stated.

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