get_marginfi_positions

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

Annotations already declare readOnlyHint=true, etc. Description adds substantial behavioral context: probes account indices 0-3, returns per-account entries with balances, USD values, health factor with interpretation (>1 safe, Infinity when no debt), and bank-level pause warnings. Contradiction false.

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?

Description is a single paragraph of 4 sentences. Every sentence adds value: opens with 'READ-ONLY', then describes action, scope, return details, and parallelism. Zero waste.

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 simple one-parameter read-only tool, the description covers return structure, health factor interpretation, aggregate totals, warnings field, and empty array case. No output schema exists, so the description adequately explains what is returned.

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 schema description for 'wallet' already includes the probing detail. The tool description repeats this without adding new meaning beyond the schema, so 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?

Description states specific verb 'enumerate' and resource 'MarginFi lending positions' for a Solana wallet. It clearly distinguishes from siblings by explicitly naming parallel tools (get_compound_positions, get_morpho_positions).

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?

Description provides clear context: it is read-only, probes first 4 accounts, and returns empty array if no positions. It mentions parallels to other tools, giving implicit guidance on when to use this vs alternatives, but lacks explicit when-not-to-use.

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