tg_send_sticker

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

Annotations already mark this as a write (readOnlyHint=false), non-idempotent, and non-destructive, and the description agrees with them. The description adds real behavioral context in the selection rules — the 'needs set' dependency for scope='set' and the 'emoji instead of an index' alternative — but it does not disclose side effects, what happens if emoji and index are both provided, or return behavior. Moderate added value beyond annotations.

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 purpose is stated in one front-loaded sentence, followed by a compact bullet-style args list where each line is a single clause carrying genuine information. No filler, no repetition of structural schema facts.

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 send action with six parameters and no output schema, the description covers all parameters and the item-selection mechanism, even cross-referencing the tg_stickers sibling for index numbering. Minor gaps remain: it never states what happens if both emoji and index are supplied, and it does not mention what the tool returns (e.g., a sent message object), which would be useful given there is no output schema.

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?

With schema description coverage at 0%, the description fully compensate: it defines chat, enumerates scope's four values, explains set's conditional dependency, cross-references tg_stickers for how index is numbered, and clarifies emoji as an alternative selector to index. Every one of the six schema parameters gains meaningful semantics from the 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?

The first sentence, 'Send a sticker or a saved GIF,' names a specific verb and resource, and the scope parameter's enumeration ('set', 'faved', 'recent', 'gifs') further pinpoints what the tool operates on. This cleanly distinguishes it from nearby siblings like tg_send_file, tg_send_location, and tg_stickers.

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?

Usage context is implied by the first sentence — use this when the payload is a sticker or saved GIF — but the description never names alternatives or states when not to use it. Given a sibling cluster of 90+ tools including tg_send, tg_send_file, and tg_send_location, explicit routing would significanly help an agent; here the choice is left to inference.

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