Preview icons

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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), so the description's added value is the output shape: a PNG plus a text result carrying each icon's license, and a hard cap of 24 icons. That is useful context for a tool with no output schema, but rendering details such as sheet dimensions or failure behavior when no icons match are unstated.

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?

Four short sentences, front-loaded with what the tool produces before the invocation modes and limits. The 'Supports size, color, background, and columns' clause mildly duplicates the schema but still serves as a quick capability scan.

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?

With 10 optional parameters, no required fields, and no output schema, the description covers the essentials: what is returned (PNG sheet + text with licenses), how to select icons, and the 24-item cap. Remaining detail (title, labels, column defaults) is fully documented in the schema, so nothing critical 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%, so a 3 is the floor, but the description adds real meaning by framing 'icons' and 'query'+'prefix' as alternatives ('Pass Iconify ids, or a search query plus an optional prefix'), which the schema only hints at via 'Search text used when icons is omitted.' It also names the tunable knobs (size, color, background, columns) and restates the 24-icon ceiling.

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 artifact: 'Render a labeled PNG contact sheet of several icons so you can compare them in one image.' This is clearly distinct from the sibling read tools (search_icons, get_icon, list_collections) because it produces a composite visual, though it never names those siblings explicitly.

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 clear context for when to reach for it ('so you can compare them in one image') and explains the two input modes: explicit Iconify ids, or a search query plus optional prefix. It stops short of exclusions or pointing to siblings for single-icon or text-only lookups.

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