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

Even though readOnlyHint=true already establishes a safe read, the description adds substantial behavioral context beyond the annotations: the image is "processed in memory and deleted immediately — never stored," internal reranking behavior ("OCR-assisted rerank of top candidates engages when retrieval is uncertain"), latency (0.3–1.7s), and the model's training source (jinero font catalog). This richly explains what the tool does behind the scenes.

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?

The description is front-loaded with the primary purpose and then efficiently covers model details, input format, privacy, output, and performance in sequence. Every sentence serves a purpose — from "trained on the jinero font catalog" (explaining coverage) to "rate limit: 5 calls/min per IP (model inference is compute-heavy)" (setting expectations). No filler or redundant phrases despite the technical density.

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 tool with no output schema and moderate complexity (ML inference, two mutually exclusive input modes, rate limiting), the description is remarkably complete. It covers the what (font identification), how (visual matching, no OCR), input preparation (tight crop, one line, Latin/Cyrillic), privacy (no storage), output (visually similar fonts with scores), operational constraints (latency, rate limits), and expectations under uncertainty (reranking behavior).

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 baseline is 3. The description adds minimal marginal value over the schema since the schema already defines parameter constraints (range 3–20, mutual exclusivity of image_url/image_base64, max 8MB). The description's only added value is the crop/quality guidance, but this doesn't meaningfully extend beyond what the schema already communicates.

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?

"Identify which font is used in an image" is a specific verb+resource statement that clearly distinguishes it from siblings like search_fonts or get_font (which imply catalog/name-based lookups). The addition of "needs NO OCR and no text" further delineates it from text-based alternatives, making the tool's unique niche explicit.

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?

Provides clear, operational guidance: "tight crop of one line of text" via either image_url or image_base64, notes Latin/Cyrillic support, and rate limits (5 calls/min). It gives clear context on how to use, but falls short of the explicit when-not-to-use or alternative-naming that merits a 5 (e.g., it never references the sibling search_fonts to contrast with text-based search).

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