shade

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

With no annotations, the description carries the full burden and does so well: it discloses cost ('cheap'), export interaction ('export_glb writes these normals while apply_modifiers is true'), modifier lifecycle ('a later shade call without it removes it'), and scope of change ('it changes normals only'). These are exactly the non-obvious behaviors an agent needs before invoking a mutation tool.

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 core mode semantics, and the sentences about modifier lifecycle and export behavior each add distinct value. It is dense and slightly long, but almost no sentence is expendable.

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?

No output schema or annotations exist, so the description must stand alone, and it covers modes, modifier behavior, and export interaction thoroughly. Minor gap: it does not say what 'names' refers to (objects vs mesh datablocks) or whether a selection is required, but that is small for a shading tool.

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 0%, so the description must compensate: it explains mode values, what 'angle' controls ('edges sharper than angle degrees stay sharp'), and what weighted_normals does and how it interacts with mode. The only parameter not addressed is names, whose meaning is self-evident from the array of object names.

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 ('Set shading of meshes') and then defines each mode's exact semantics, including the discriminating example (a cube stays crisp, a sphere becomes smooth). It also explicitly distinguishes itself from the sibling tool sculpt at the end, so an agent can tell what this tool does and does not do.

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 a concrete when-to-use rule for the weighted_normals option ('parts with both bevels and flat chamfers, where no single angle works') and names the alternative for a related-but-different need ('to move vertices use sculpt'). It does not spell out when to prefer flat vs smooth vs auto beyond the mode definitions, but the context is clear.

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