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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety and external reach are covered structurally. The description does add that a "live NEAR Intents quote" is fetched, implying a real-time external dependency that may be slow or fail, but it says nothing about latency, caching, partial-failure behavior, or what happens when no quote exists.

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?

A single front-loaded sentence that leads with the action and then enumerates the computed fields; every clause corresponds to an output. The list is dense but no sentence is wasted, and there is no redundant restatement of the tool name.

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's enumeration of returned metrics is exactly the compensating information an agent needs, and it covers them well. The remaining gap is input-side: identifier format and failure/empty-quote behavior are unaddressed for what is a fairly rich aggregate read.

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?

There is exactly one parameter (token_id) with 0% schema description coverage, so the description must carry the burden — yet it only says the tool operates on "one Pusaka." It never states that token_id is the identifier, nor its expected format (numeric string, contract address, or otherwise), leaving an agent to guess at the single input that gates the whole call.

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 action ("Full due diligence on one Pusaka") plus a concrete inventory of what is computed: verified BTC/USD value, NEAR Intents exit quote, ETH safe-vs-at-risk split, listing premium, LTV, APR, coverage ratio, sign epoch. This makes the tool's scope unmistakable as a comprehensive single-token report, distinct in spirit from narrower siblings like pusaka_credit_record or pusaka_swap_status, though it never names an alternative.

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 only implied: the phrase "Full due diligence" suggests this is the broad inspection call rather than a targeted one, and the outputs listed hint at loan/collateral evaluation scenarios. There is no explicit statement of when to prefer this over pusaka_audit, pusaka_overview, or the narrower record tools, and no preconditions are given.

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