upload_sticker_pack

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

Annotations cover the safety profile (readOnlyHint=false, openWorldHint=true, destructiveHint=false), but the description adds what annotations cannot: the pack becomes public to anyone with the link, it cannot be deleted through this tool, invalid or oversized images error out, and the return is {url}. These are consequential, non-obvious behaviors for an irreversible publish action.

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 purpose, then path rules, side effects, error behavior, and the sibling pointer — every sentence carries weight. It is a dense single paragraph rather than scannable structure, which slightly hurts fast parsing, but there is no 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?

With no output schema, the description supplies the return shape ({url}) and the failure mode (error on invalid/oversized packs). Combined with the visibility and deletion constraints, an agent has everything needed to invoke this correctly and warn the user about permanence.

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% for the single path parameter, so the baseline would be 3, but the description materially enriches it: the value may point to a manifest.json (with images beside it) or a zip, and must sit inside an enumerated allowlist of folders while avoiding hidden folders. That is real semantics beyond the schema's one-line type description.

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 ('Publish a new sticker pack... to Signal's servers') plus the concrete outcome (shareable signal.art link). It explicitly distinguishes itself from add_sticker_pack, which installs existing packs rather than publishing new ones, so an agent can route 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?

Gives both the positive trigger (publishing your own images as a new pack) and the alternative with its condition ('Use add_sticker_pack to install an existing pack'). The allowed-folder constraint and the hidden-folder exclusion further define when a call will be valid.

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