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

The annotations already declare readOnly, idempotent, non-destructive, openWorld, so the description's added value is in disclosing data provenance: finalized history plus current on-chain state, pricing sourced from Jupiter Price v3 / Raydium stable-leg and explicitly labeled current rather than historical. It also reveals the discovery mechanism (personal-position signatures, Anchor events, current equity), which implies scanning cost, but it doesn't state latency expectations or what happens when history isn't yet finalized.

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 purpose is front-loaded, and most sentences carry real information, but it is a single dense paragraph mixing formulas, acronyms (TE, HPR) and caveats with no structural separation, and TE is used without definition. It is information-dense but not easily scannable.

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 six-parameter read-only computation tool with no output schema, the description does substantial work: it names return fields (holdingDays, feeOnlyAprPct, annualizedReturnPct), states the annualization formulas, and explains the pricing model and history discovery. It is only partially short of complete because, with no output schema, the return payload beyond those few named fields is left unspecified.

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 83%, so the baseline is 3. The description does add real meaning beyond the schema by explaining that refreshHistory and historyAfterSignatures must be used together after a transaction (the schema gives historyAfterSignatures no description at all) and by clarifying that skipPricing leaves token-native metrics intact — but it never explains maxSignatures' scan-cost tradeoff or the wallet parameter's verification-only role.

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?

The description names a specific verb and resource: computing holding-period return (HPR) and realized fee APR for a Raydium CLMM position NFT, drawing on finalized history and current on-chain state. It explicitly contrasts its metric with 'Raydium pool 24h feeApr,' which separates it from pool-level tools like get_pool_range_apr, though it never names a sibling tool directly and the density of jargon (TE, HPR) blunts first-read clarity.

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?

It gives concrete operational guidance: prefer token-native metrics for same-asset RWA wrap pairs, treat USD as optional/secondary, and after submitting a position transaction use refreshHistory=true together with historyAfterSignatures to force finalized history. What's missing is explicit routing guidance versus siblings such as get_position_range_status or get_pool_range_apr — the agent must infer the boundary from the metric contrast alone.

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