render_sheet

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 orthographic/shared-scale rendering model, the grid units, the axis colour convention, and the output legend format ('name to #rrggbb') plus the caveat that the lit picture differs in brightness. It does not mention cost, time, or whether anything in the scene is mutated, which is a minor gap.

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 an 'Overview:' summary and tightly organized around what the image contains, then sibling routing. Some sentences are run-on and the backtick-heavy syntax is slightly noisy, but there is little genuine waste.

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-param render tool with no annotations and no output schema, the description covers the visual contract (views, scale, grid, axes, legend) and sibling choice well. It falls short only on the `size` parameter and the meaning of the `views` values, which an agent would otherwise have to guess.

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 0% across 4 params, so the description must compensate. It meaningfully explains `names` ('limits the objects (with children)') and `color_by` (object colouring plus legend), but says nothing about `size` and only obliquely implies the `views` enum through 'several fixed views'. Half the parameters remain unexplained.

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+resource ('render_sheet' produces 'one image with several fixed views') and immediately characterizes the output: orthographic flat views sharing one scale, with a metre grid and coloured world axes. It also explicitly distinguishes itself from the two rendering siblings by naming them.

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 explicit routing: 'Use render_view for one free angle, a close-up or a check mode, render_final for the lit picture through the scene camera.' The agent knows exactly when to pick this tool over its two closest alternatives.

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