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

Annotations declare destructiveHint=true and openWorldHint=true, and the description substantiates both: it discloses that dedupe replaces a matching family+weight+style face, that it does NOT verify the uploaded filename exists (paralleling add_image_layer), and that a URL is not fetched at call time but downloaded later by the renderer and every opening browser. The CORS caveat is exactly the kind of behavioral context annotations cannot convey.

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?

Purpose and the built-in rejection are front-loaded, and nearly every sentence carries actionable content (dedupe, no-verification, CORS, deferred fetch). It is on the long side and the trailing docs URL plus some restatement of schema fields could be trimmed, but there is little true filler.

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?

An output schema exists, so return values need not be explained, and the description still covers the whole workflow: what registers, how layers reference it, dedupe behavior, failure/caveat modes (CORS, no filename validation), and the downstream calls. Nothing essential for correct invocation is missing.

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 100% and the schema already describes family, src, weight, and style. The description still adds meaning beyond it: src accepts the exact filename an upload returned, and the weight/style pair is dedupe-scoped ("replacing a matching face"), which the schema does not state. Slight edge over the baseline 3.

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 ("Register a typeface Morpha does NOT ship") and immediately scopes it against the built-in catalogs, explicitly naming list_fonts as the sibling whose output is excluded. An agent can distinguish this from list_fonts and the add_text_layer/set_layer_text tools without opening a schema.

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 when-to-use (non-shipped typefaces), when-not (built-in families from google/bunny/fontshare/fontsource/velvetyne are REJECTED), and the alternative action for that case (set font_family directly). It also routes the follow-up step (add_text_layer / set_layer_text) and prefers upload over URL for CORS reasons.

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