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

Annotations already declare destructiveHint=true, non-idempotent and open-world, so the risk profile is covered. The description adds real value beyond them: the auth key format and where to obtain it, that the order is recorded before placement, and the instruction to confirm with the member because real money moves. The phrase 'a sell is never refused for the token's read' is cryptic but hints at no pre-trade safety gate.

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?

Content is front-loaded with purpose first, then prerequisites, behavior, and safety. It is slightly dense and one clause ('never refused for the token's read') is ambiguous filler, but each sentence largely earns its place.

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 correctly redirects the agent to agent_order to retrieve the result, and it covers auth, irreversibility context, and human confirmation for a real-money mutation. Only the address parameter's meaning is left unexplained.

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 description coverage is 0%, so the description must carry both parameters. It explains pct well (percent of holding, 1-100), but the address parameter is never mentioned or disambiguated, leaving half the input undocumented.

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 gives a specific verb (sell), resource (Robinhood Chain token held in the member's wallet), and scope (part or all, as percent of holding 1-100). This cleanly separates it from the sibling agent_buy without needing to open 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?

It states the prerequisite (agent key from PumpPill's Telegram bot), the required human-in-the-loop step (confirm with the member first), and the follow-up (poll agent_order for the result). It does not name an explicit condition for choosing this over agent_buy, but the buy/sell split is self-evident from the purpose.

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