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

With no annotations supplied, the description carries the full burden and does so well: it discloses size and format limits (max 5 MB, png/jpeg/webp/gif), that results are not stored, that it will not name people, and the payment model ($0.006 USDC via x402 on Base or Solana). It even documents failure behavior — 400 before payment for a bad/private URL, 422 and not charged for non-images — which is exactly the cost/side-effect context an agent needs before spending money.

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 trigger, then input, output, exclusions, example, and price in a compact telegraphic sequence — every clause carries information. It reads as bullet fragments rather than prose, which costs a little readability but wastes nothing.

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 no-annotation, no-output-schema tool, the description covers the full call lifecycle: what it does, required input and limits, how to switch between free-text and structured output, what comes back, what it refuses, and what it costs. Nothing an agent needs in order to invoke it correctly appears to be 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%, so the baseline is 3 and the schema already documents all three parameters including the error semantics. The description adds some meaning the schema lacks — the concrete structured fields returned when json=true (objects, text, people count, colors) and the 1000-char question limit — but these are partly restatements of accepted value sets.

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 — understand a picture — and enumerates the concrete image types (screenshot, product photo, chart, scene) it handles. It also explicitly routes exact-text work to the sibling convert_ocr, so an agent can separate it from the nearest alternative without opening either 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?

Opens with an explicit 'Use when an agent must understand a picture' trigger and names convert_ocr as the alternative for exact text, which is real routing guidance. It stops short of a full when-not-to-use list (e.g. generating images vs. understanding them, or transcribing audio), so it is strong but not exhaustive.

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