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

With no annotations provided, the description carries the full burden. It discloses the pricing model ($0.10 per call), the revenue model (x402), and behavioral traits like dropping honeypots/balance-modifiable tokens during safety screening. It doesn't disclose rate limits or response time, but the core behavioral disclosure (paid, safety semantic) is present.

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 description is compact at roughly 50 words yet covers purpose, filtering, safety, and output. It front-loads the pricing note and primary purpose. Slightly dense with parentheticals, but efficiently packed without redundancy.

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 moderately complex multi-parameter screener with no output schema and no annotations, this description covers the key elements: purpose, filters, safety behavior, and output fields. It doesn't describe the ranking criteria in detail, but given no output schema and no annotations, it does a solid job. Minor gaps around what 'ranked opportunities' means and the exact safety screening limitations.

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% and each parameter already has description with defaults (e.g., mode defaults to trending, limit defaults to 10 max 20, network defaults to base). The description adds context around how parameters interact (safe_only running on Base tokens), and clarifies that 'safe_only' drops dangerous tokens. Most meaningful semantics are already in the schema, so the description adds marginal value.

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 uses a specific verb+resource structure ('Token screener: trending or newly-launched pools on a chain') and clearly specifies the scope (chains, filtering criteria, safety screening). It distinguishes itself from siblings like 'trending' by adding liquidity/volume filters and safety screening, and lists concrete outputs (price, liquidity, volume, buys/sells, safety flags).

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 states the tool is for finding 'trending or newly-launched pools' with filtering criteria, which establishes a clear context. It doesn't explicitly name alternatives or when-not-to-use, but the sibling tool 'trending' is implicitly differentiated by the additional filtering and safety screening capabilities. The pricing note also sets usage expectations.

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