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

With no annotations, the description carries full behavioral burden. It discloses the auto-discovery mechanism, hourly refresh, activity count semantics, and that 'discovered' entries are not yet named. It doesn't cover all possible behaviors (e.g., pagination, rate limits), but the disclosed traits are significant and non-obvious.

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?

Two sentences, front-loaded with the purpose, then details. Every sentence adds value: the first identifies the resource and scope, the second explains the merged seed/auto-discovery behavior and usage context. No redundancy or fluff.

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?

Given the tool's complexity (multi-chain, merged seed, hourly refresh, activity counts), the description covers the core semantics well. The output schema handles return details, and the description provides the necessary context for an agent to understand what the tool offers, including the pointer to describe_program for next steps.

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?

Only one parameter (chain) with 100% schema description coverage, so the schema already documents it. The description repeats the chain list but adds no additional parameter semantics beyond what the schema provides, so the baseline 3 applies.

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 clearly states the tool discovers on-chain programs/contracts across all supported chains, with a specific verb ('Discover') and resource. It distinguishes itself from siblings by explicitly mentioning the merged curated/discovered nature and pointing to describe_program for introspection.

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 explicitly says when to use ('learn what is actually active on-chain right now') and names the alternative tool ('then describe_program to introspect any specific address'). However, it doesn't provide explicit when-not-to-use conditions or exclusions.

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