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

With no annotations, the description carries the full burden and does so well: it discloses the data source (GeckoTerminal), the 20-result cap, cost ($0.01), that checks are heuristics and not an audit, and the important limitation that B20 native tokens cannot be checked by bytecode. It also enumerates exactly which risk signals are computed (Sourcify verification, proxy, owner type, mint/pause/blacklist/fee functions, copycat flag).

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?

Dense but front-loaded: what it is, what's risk-checked, what's returned, then cost. The risk-signal list is long yet each item is a distinct decision-relevant field, so little is wasted.

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 and no annotations, so the description must describe the payload — which it does by listing pool DEX, age, liquidity, FDV, 1h buys/sells and the risk flags. It stops short of stating the response envelope or ordering guarantee, a minor gap for a single-parameter listing 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?

The single 'limit' parameter has 0% schema description coverage and no enum, so the schema provides only a pattern. The description compensates with 'up to 20', which explains the legal range and the default behavior implicitly; it does not clarify what happens if limit is omitted, keeping it short of a 5.

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+resource ('newest token launches on Base') plus the venues covered (Uniswap, Aerodrome, Bankr, launchpads), which cleanly separates it from launch_feed, bsc_launch_feed and solana_launch_feed. An agent can pick this one for Base without opening the 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?

The chain scoping and 'risk-checked at request time' implicitly tell you when this is the right feed, and the copycat/B20 caveats hint at what it can and can't answer. However, there is no explicit routing to token_deep_scan, token_report or base_contract_risk when an agent needs a deeper per-token audit.

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