preview_sticker

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

With no annotations, the description carries full burden. It declares 'Read-only,' mentions the data source ('public sticker CDN'), and describes output labeling ('labeled with its stickerId + packageId for send_sticker'). No side effects or auth needs are discussed, but the read-only nature is clear.

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 sentences, each purposeful. First sentence states core action and output format. Second explains parameter usage. Third details output labeling. Fourth declares read-only. No wasted words, well front-loaded.

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?

No output schema, but the description compensates: describes output as MCP image content labeled with IDs. It also mentions the source (CDN) and linkage to send_sticker. Lacks details on image formatting (e.g., size), but is sufficient for a preview tool.

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%, baseline 3. The description adds meaning: clarifies that without stickerId it shows the 'first' stickers, explains the relationship to list_stickers, and mentions default limit (8). This goes beyond the schema's simple descriptions.

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?

The description clearly states the tool's action: 'Show sticker preview images...so you and the user can SEE them before sending.' It specifies the verb 'preview' and resource 'sticker images', and distinguishes from siblings like list_stickers (listing) and send_sticker (sending) by emphasizing the preview-for-selection purpose.

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?

The description explains when to use which parameters: 'Give a packageId...to preview its first stickers, or add a stickerId to preview just one.' It also notes the default limit. However, it does not explicitly state when not to use this tool (e.g., if you already know the sticker, use send_sticker directly).

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