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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=true, idempotentHint=false), so the bar is lower. The description adds genuine behavioral context: it runs against 'one validated ledger,' discloses whether 'the marker chain was exhausted' (truncation/pagination completeness), and promises the 'exact counting methodology,' which is valuable disclosure beyond structured fields.

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 enumeration of returned metrics before the interpretive caveat. No filler; each clause contributes (returned fields first, then semantic warning).

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 no-param, read-only tool with no output schema, the description enumerates the return contents and caveats interpretation, which is close to complete. Minor gap: it doesn't state a ledger-selection mechanism even though it operates on 'one validated ledger.'

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 zero parameters, the baseline is 4. There is nothing to document, and the description does not attempt to introduce undocumented inputs.

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 scoped precisely: a 'complete trust-line enumeration of the ASTEROID issuer on one validated ledger,' naming exactly the outputs (total trust lines, non-zero balance lines, marker exhaustion). It implicitly separates itself from holder-count siblings like get_token_stats by clarifying 'a trust line is not a person,' though it does not name a sibling explicitly.

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 is implied through the caveat that trust lines != holders, which tells the agent when this metric is (and isn't) appropriate. However, no explicit when-to-use or alternative selection (e.g., vs get_supply_state or get_token_stats) is provided.

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