Alertio

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds substantial context: the exact return contents (health factor, blended threshold, liquidation-trigger collateral drop, collateral value at liquidation), the formula, and the fact that no on-chain lookup occurs. This is well beyond what the annotations convey.

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-loaded with the core purpose before the formula, supported protocols, and example queries, so an agent gets the essentials first. The four quoted example prompts are useful for intent matching but make the block noticeably long and slightly repetitive.

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 4-parameter computation tool with a full output schema and read-only annotations, the description covers purpose, inputs, formula, supported protocols, return fields, and usage triggers. Nothing an agent needs to invoke it correctly is missing.

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%, so the baseline is 3, but the description earns extra credit by stating the formula HF = (Σ collateral value × liquidation threshold) ÷ debt, which clarifies how the collateral and debt parameters are actually combined. It also explains the optional collateral_drop_pct / debt_change_pct as what-if simulations. It stops short of adding format or edge-case detail beyond the schema.

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 first sentence states a precise verb+resource ("Calculates a lending health factor from position inputs") and immediately scopes it against wallet-based siblings with "no wallet or on-chain lookup required." It also names the protocols covered (Aave, Morpho, Spark, Kamino), so an agent can distinguish it from simulate_liquidation and scan_wallet without reading the 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?

It explicitly enumerates when to use the tool via four quoted example prompts, which directly map user intents to this tool. It does not, however, name the alternative to use instead of this one (e.g. simulate_liquidation) or state when-not conditions, so it falls short of a 5.

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

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds real domain behavior beyond that: it scopes coverage to 7 chains, explains the utilization-above-optimal mechanism that spikes borrow APY, and discloses that frozen/paused market state is surfaced.

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 the return contents and scope before the edge-case note and the example queries, so the first sentence already answers what the tool does. The five example questions are longer than strictly necessary but each maps to a distinct query shape, so no sentence is pure filler.

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, return values need not be enumerated, yet the description still names the key fields. Filters, chain coverage, and the optional-parameter behavior are all covered; the only omission is any note on data freshness or refresh cadence for what is inherently time-sensitive live rate data.

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 description coverage is 100%, with both optional filters documented including case-insensitivity and omit-for-all semantics, so the baseline is 3. The description's chain list re-confirms the enum but adds no format or syntax detail beyond what the schema already states.

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 (returns Aave V3 market utilization rates, supply APY, borrow APY across 7 named chains) and adds the frozen/paused status dimension. An agent can distinguish this from siblings like calculate_health_factor or simulate_liquidation, which are position-level tools, without opening either 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?

Explicitly frames usage with 'Use this when asked:' followed by five concrete example questions covering per-asset, per-chain, cross-market, rate, and frozen-market intents. It never names a competing tool or states a when-not-to-use condition, which keeps it short of a 5.

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

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond structured fields: the upstream source (DeFiLlama), the coverage set ('and more'), and the specific 0.5% deviation rule that produces a depeg signal. It doesn't discuss freshness/latency beyond 'real-time' or error behavior, keeping it short of a 5.

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-loaded with purpose and return shape before the trigger examples. The four example queries are slightly verbose but each demonstrates a distinct query pattern the tool answers, so they largely earn their place.

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 single-optional-param read tool with a full output schema and complete annotations, the description covers what the data is, where it comes from, the fields returned, and the depeg threshold. Nothing needed to call it correctly is missing, and return-shape detail is left to the output schema.

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 description coverage is 100% and the single optional `symbol` parameter is already fully documented (case-insensitive, omit for all). The description adds no syntax or format detail beyond what the schema provides, so the 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 verb+resource ('Returns real-time USD peg data for the top stablecoins'), names concrete coins, the data source (DeFiLlama), and the exact fields returned (price, deviation, market cap). An agent can distinguish this from every sibling (health factor, utilization, wallet scans) purely from the description.

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?

Explicitly says 'Use this when asked:' and follows with four concrete trigger queries covering both single-coin ('What is DAI trading at?') and market-wide ('Which stablecoins are showing depeg signals right now?') use cases. Sibling tools are unrelated domains, so no exclusion routing is needed; the trigger set is unambiguous.

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

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so safety is covered. The description adds genuine domain context beyond structured fields: health factor < 1.0 denotes a liquidatable position, which is what makes the returned data actionable.

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 purpose and the key interpretation rule, then the trigger examples in one compact block. Every sentence earns its place; no filler.

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 single-param read tool with rich annotations and an output schema, the description covers purpose, trigger conditions, and the critical interpretation threshold. Nothing needed to call or interpret it is missing.

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 description coverage is 100% and the single 'wallet' parameter is fully documented in the schema with base58 pattern and example. The description adds nothing about parameter format, so the 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 verb (scans) plus resource (Solana wallet address) and narrows scope to Kamino lending positions with a precise output summary (borrowing positions, health factors, liquidation risk). An agent can distinguish it from scan_ton_wallet and the generic scan_wallet without inspecting schemas.

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?

Provides explicit trigger phrasing ('Check Kamino health for this Solana wallet', 'Is this Solana address at risk of liquidation?') that maps intent to tool. It stops short of naming the alternatives (scan_wallet, scan_ton_wallet) or stating when NOT to use it, so it is clear context without exclusions.

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

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive behavior, so the safety profile is covered. The description adds useful domain behavior: what is fetched (active borrowing position) and the critical interpretability rule that health factor < 1.0 means liquidatable. It does not mention failure modes for wallets with no position or unsupported addresses.

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-loaded with the core action and return values, followed by the health-factor interpretation rule and example utterances. The three quoted example questions are longer than strictly necessary but do earn their place by improving intent matching; otherwise the text is tight.

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?

The tool is a single-parameter read with a full output schema, so return-field documentation is unnecessary, and the description covers purpose, interpretation of the key metric, and usage triggers. The only gap is the absence of guidance relative to the closely related calculate_health_factor and scan_wallet siblings.

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 description coverage is 100% and the schema already specifies the 48-character friendly format starting with EQ or UQ with an example, so there is nothing for the description to compensate for. The description adds no additional parameter information beyond the schema, so the baseline of 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 verb ('Scans'), resource ('a TON wallet address'), the protocol context ('EVAA lending protocol'), and the return ('active borrowing position with health factor and liquidation risk'). This clearly distinguishes it from siblings such as scan_solana_wallet, scan_wallet, and calculate_health_factor.

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 explicit trigger phrasing ('Use this when asked: ...') with three representative user questions, which is strong routing guidance for an agent. It does not, however, state when NOT to use it or why one would prefer calculate_health_factor or scan_wallet over this tool, so alternatives remain unaddressed.

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

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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so the safety profile is covered. The description adds genuinely non-obvious domain context — the exact protocol/chain coverage and the rule that health factor < 1.0 means liquidatable — which the annotations cannot express.

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-loaded with the purpose and return shape before the longer protocol enumeration, and the health-factor rule and trigger phrases are well placed. The protocol/chain list is dense but earns its space by defining coverage boundaries; it is slightly verbose for a single-parameter tool.

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?

An output schema exists and annotations cover the safety profile, so the description need not explain return format or permissions. Coverage limits, the liquidation threshold, and example intents are all present — nothing an agent needs to call this correctly is missing.

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?

Only one parameter and schema description coverage is 100%, so the schema already documents the 0x address format and length. The description adds nothing further about the parameter, so the baseline 3 is correct.

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 ("Scans an EVM wallet address") and enumerates exactly what it returns: every active borrowing position with health factors and liquidation risk. The protocol/chain scope (Aave V3/V4, Spark, Morpho, Euler, Moonwell) clearly separates it from scan_solana_wallet and scan_ton_wallet.

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?

Gives explicit trigger phrases ("Is this wallet at risk of liquidation?", "Which protocols is this wallet borrowing from?") that map user intent to this tool. It does not name the alternative tools directly — an agent must infer that non-EVM wallets belong to scan_solana_wallet/scan_ton_wallet — but the EVM scoping makes that routing nearly unambiguous.

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

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the burden is lower. The description adds real substance beyond them: the exact formula (newHF = currentHF × (1 − drop%)) and the output behavior (per-position HF changes plus AT RISK / DANGER / LIQUIDATED flags). It stops short of stating protocol coverage limits or failure modes for non-lending wallets.

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-loaded with purpose, then the formula, then output shape, then usage cues — a sensible ordering. The four example queries are somewhat repetitive and could be trimmed, but each reinforces a distinct framing (single-asset drop, market crash, stress test, liquidation proximity).

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?

An output schema exists, so return values need not be described, yet the description still summarizes them helpfully. With two fully documented required parameters, full annotation coverage, and stated scope across five protocols, nothing an agent needs to invoke this correctly is missing.

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%, so the baseline is 3. The description adds meaning beyond the schema by explaining collateral_drop_pct as a wholesale collateral-value multiplier via the newHF formula, clarifying that the pct applies to the entire collateral side rather than a single asset.

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 (simulate) and resource (impact of a collateral price drop on active EVM lending positions), and names the protocols covered (Aave V3/V4, Spark, Morpho, Euler, Moonwell). An agent can distinguish it from calculate_health_factor (static current HF) and the scan_* siblings 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?

Gives explicit triggering conditions via four natural-language user queries ('What happens to this wallet if ETH drops 30%?', 'Would this wallet survive a 40% market crash?', etc.), which is strong when-to-use guidance. It does not name an alternative tool (e.g., calculate_health_factor for the no-drop case) or state when NOT to use it, so it falls short of the 5 bar.

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