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

Annotations cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower, and the description still adds real context: loan_count/loan_balance_usd appear only when the loan book is read on-chain, trailing_90d_apy_percent is a share-price-change annualization and explicitly *not* an issuer-quoted yield, and unknown ids return a documented not_found payload. It omits auth/rate-limit details, but for a read-only data tool the interpretive caveat is the important disclosure.

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?

Front-loads what the tool is, then the usage trigger, then field semantics and the return/error shape. A dense but efficient description; the inline JSON key list is terse but earns its place given no output schema exists.

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 no output schema, the description steps in to describe the return object and the not_found error shape, plus the conditional presence of loan fields. That covers what an agent needs; only minor gaps remain (no pagination/refresh semantics, and the JSON key listing is implicit about types).

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 both parameters (asset, response_format) carry their own descriptions including the enum and default. The description's mention of "USD.AI and GAIB" loosely maps to the asset ids but adds no syntax or format detail 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?

States a specific resource with scope: on-chain figures for the USD.AI and GAIB compute vaults, and enumerates the data points it returns (tokens outstanding, share price, trailing 90-day figure). This is clearly distinguishable from siblings like get_asset, market_totals, or gpu_price_index.

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?

"Call this for tokens outstanding, vault share price, and the trailing 90-day figure" gives clear situational context for selecting the tool. It stops short of naming an alternative or stating when *not* to use it (e.g., versus get_asset for single-asset queries), so it lacks explicit exclusions.

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