silhouette_add_text

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

Annotations already declare the safety profile (non-readOnly, non-destructive, non-openWorld), so the description's job is to add behavior. It does: it discloses font resolution behavior including a fallback to built-in geometric vectors when a TTF/OTF isn't available, plus the anchoring convention. It stops short of saying whether repeated calls create duplicate shapes or what identifiers are returned for the new contours.

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?

Two sentences, front-loaded with the action and mechanism, then the geometry convention. The parenthetical about fallback fonts is dense but earns its place by explaining a failure mode.

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 11-parameter mutation with no output schema and zero schema coverage, the description is adequate but thin: it never clarifies units/axes for size_mm or rotation_deg, or what layer and label do. An agent can probably call it correctly, but placement and sizing semantics rest largely on parameter names.

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 carry parameter meaning, and it only covers 5 of 11 parameters. It does add real, non-obvious semantics for those five — the align values ('left','center','right') are stated even though the schema has no enum, and x_mm/y_mm are defined as the top edge anchored horizontally by align. size_mm, rotation_deg, letter_spacing_mm, layer, label, and design are left to name inference.

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 chain and resource: convert text to vector cut/score outlines and add glyph contours to the design. This clearly separates it from sibling shape adders (add_circle, add_rectangle, add_star), which place primitives rather than font-derived geometry.

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 no when-to-use or when-not-to-use guidance, and no indication of when the 'built-in geometric vector fallback' would be preferred or what triggers it. An agent must infer that this is simply the text counterpart to the other add_* shape tools.

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