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

Annotations already cover read-only, idempotent, non-destructive behavior, but they do not cover cost. The description adds the critical commercial context: 'Paid USDC on Base', per-bundle pricing, and that unknown ids return 404 with no charge. That is exactly the behavioral disclosure an agent needs before invoking a paid read.

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 core constraint ('Paid USDC on Base') is front-loaded, followed by usage, then the complete bundle enumeration. The dense semicolon-separated list is long but every clause carries pricing, contents, or error behavior, so no sentence 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?

With an output schema present, the description needn't explain return values, and it still adds 'Same JSON as the single cards' as a useful compatibility note. Payment, pricing, contents, failure behavior, and a cross-reference to list_filers are all covered, leaving nothing an agent needs to call it correctly.

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 the enum already lists SEMIS, CENTRALBANKS, and BRICS, but the description goes further by unpacking what each id contains and what it costs ($0.06 and $0.08 respectively). This adds real meaning beyond the schema's bare 'Bundle id' label.

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 and resource ('get_bundle' → every card in a set at once) and immediately scopes it as a cheaper bulk alternative to buying cards singly. The parenthetical examples (chips filings, major central banks, BRICS central banks) make it distinguishable from sibling singles like get_cpi and get_macro without opening any 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?

Says explicitly when to call it ('when you need every card in a set at once') and what the alternative is ('cheaper than buying them singly'). It also states the failure branch ('Others return 404 (no charge)') and points to list_filers for discovery, so the agent knows both when and when not to use it.

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