NLYRA — the risk layer of Robinhood Chain

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered; the description adds real behavioral value by spelling out what the live check performs (an actual sell-back test with taxes, an ongoing price/liquidity watch, a launch grade). It still says nothing about latency, caching, rate limits, or what happens for an invalid/unknown token address.

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, then the data inventory, then the trigger for use; no filler sentences. The middle clause is a dense comma-separated list, but it stays readable and earns its space.

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 does the necessary work of describing the returned data (risk level, sell test, launch grade, price/liquidity/volume/holders). Annotations cover the safety profile. The one missing piece is sibling disambiguation against check_tokens_risk.

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 a single 'token' parameter with 100% schema description coverage and an explicit address regex, so the schema fully documents it. The description adds no additional meaning (e.g., chain constraints beyond Robinhood Chain, token-type limits), which is the correct baseline of 3 when schema coverage is complete.

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 ('live Risk Level for a token on Robinhood Chain') and enumerates what the risk assessment covers (sell test, taxes, price/liquidity watch, launch grade). However, it never distinguishes itself from the near-identical sibling check_tokens_risk, leaving the agent to infer which one to call.

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?

The closing 'Use it before suggesting any buy' gives one clear usage context, but there is no when-not guidance and no mention of the obvious alternative check_tokens_risk (plural/batch) for multi-token checks. Usage is implied rather than routed.

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 read-only, idempotent, open-world, non-destructive behavior. The description adds the batch limit (up to 25) and lists the return fields (level, sell test, live watch, reason), which is useful since no output schema exists. It does not discuss rate limits or auth needs, but those are less critical for a read-only screening call.

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 sentence that front-loads the core purpose and scope, then adds return fields and usage guidance without any waste. Every clause earns its 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 simple batch read-only tool, the description gives the batch limit, return fields, and routing to the single-token sibling. Annotations cover the safety profile and the schema fully covers the single parameter, so nothing essential 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%, so the single tokens parameter is fully documented in the schema. The description reinforces the 25-token maximum and Robinhood Chain context, but adds no new syntax, format, or meaning beyond what the schema already provides.

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 (check risk), resource (up to 25 Robinhood Chain tokens), and scope (one call), and names the sibling check_token_risk for deeper single-token inspection. An agent can distinguish this batch screening tool from the single-token sibling 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 says it is good for screening a list before looking closer with check_token_risk, giving clear when-to-use and an alternative. It does not explicitly state when not to use it (e.g., for a single token), but the context is clear.

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/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond that: that duplicate symbols exist, that results are ranked candidates, and what fields come back (address, liquidity, Risk Level) — important since there is no output schema.

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?

Three tight sentences: purpose first, then the disambiguation caveat, then the actionable takeaway ('Always act on the address, not the symbol'). Nothing is padded or redundant.

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-parameter lookup with no output schema, the description does the necessary work of naming the returned fields and the ambiguity the tool resolves. It leaves open whether results are paged, ranked, or limited in count, which is a minor gap.

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 single param already documents the accepted formats (symbol, name, 0x address). The description restates the same three formats without adding syntax, casing, or partial-match rules, so it adds no meaning 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?

States a specific verb (look up) plus resource (token) and scope (by symbol, name or address on Robinhood Chain), which is clearly distinct from siblings like check_token_risk or scan_contract. An agent can tell immediately what this tool returns: disambiguated candidate tokens.

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 clear contextual guidance — that symbols are ambiguous due to copies and fakes, so this tool should be used to disambiguate before acting, and that the address (not the symbol) is the stable identifier. It does not explicitly name when to route to check_token_risk or scan_contract instead, so it stops short of full alternative routing.

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 destructiveHint=false, so the safety profile is covered. The description usefully adds provenance ('NLYRA's own node') and an equivalence claim ('same data as The Desk's chart'), but says nothing about rate limits, freshness, or auth.

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?

One tight sentence that front-loads the returned fields and ends with the source/provenance note. No filler; only slightly compressed given the parenthetical field list.

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 read-only candle fetch with 3 params, annotations cover safety and the schema covers parameters; the description even enumerates returned fields despite there being no output schema. It is missing only rate-limit/freshness context, which is non-critical.

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 67%: the candles and timeframe parameters already carry descriptions with defaults, while the required 'token' param only has a regex pattern. The description adds no parameter meaning (no syntax, no default restatement), so the schema does the heavy lifting — baseline 3 is appropriate.

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: candles (OHLC, USD volume, trades) for a Robinhood Chain token, plus the data source ('NLYRA's own node'). An agent can tell it returns price candles rather than risk/quote data, though it never names a sibling to contrast against.

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?

No when-to-use or when-not-to-use guidance. With overlapping siblings such as market_overview and quote_trade, the description gives no signal about which to choose for current price vs historical candles vs market-wide data.

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 (readOnly, idempotent, non-destructive, openWorld), so the description's added details about the status enumeration and returned payload (block, gas, explorer and The Desk links) are genuine extra context. It stops short of describing behavior for an unknown or malformed tx_hash, which keeps it from 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?

One compact sentence with zero filler that leads with the core outcome and then lists the returned fields. It reads as a noun fragment rather than a verb-led statement, a minor structural weakness.

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 tool with no output schema, the description covers what the call resolves to and what comes back, which is most of what an agent needs. The only real gap is error behavior for invalid or unrecognized hashes.

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 0% and the description never references the single tx_hash parameter or its expected 0x-prefixed 64-hex format. The regex pattern in the schema partially compensates, but the description adds no semantic meaning of its own.

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 states a specific resource (a Robinhood Chain transaction) and enumerates the exact outcome it reports (pending, confirmed, failed) plus the data returned (block, gas, explorer links). It is clearly distinguishable from every sibling, none of which deals with transaction status, though it lacks an explicit verb like 'retrieve'.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives. The agent can infer it is for checking a known tx_hash, but the description never says so or when another tool (e.g. scan_contract) would be more appropriate.

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=true, idempotentHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context by warning that backtests are estimates on past prices, not promises. However, it doesn't mention rate limits, freshness, or pagination; a 3 is appropriate given annotations do the heavy lifting.

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 sentence covers the resource, funding model, returned fields, and a caveat, with no obvious filler. It is front-loaded and efficient, though the density is high.

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 read-only, parameterless list tool with no output schema, the description adequately conveys what is returned and the nature of the backtest data. No output schema exists, so explaining return values is appropriate, and it does so. Missing only minor details like refresh cadence.

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?

The tool has zero parameters, so the baseline is 4. The description appropriately spends its length describing the returned content (band, step, min/suggested investment, backtest) rather than parameters, which is correct for a paramless list endpoint.

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 (listing bot presets published by 'The Desk' for Robinhood Chain tokens), including the bot types and the fields returned. It is clear what is being fetched, though it does not explicitly differentiate from sibling tools like prepare_bot.

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 implied by the description—this is the discovery step before preparing a bot—but there is no explicit when/when-not guidance or reference to alternatives such as prepare_bot. The context is inferable but not stated.

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 the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the bar is lower. The description adds genuine context beyond them: data provenance ('from NLYRA's own node') and freshness ('live read'), plus the fact that every entry carries a Risk Level. It omits refresh cadence, caching, and error behavior.

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 sentence that front-loads the core concept ('A live read of Robinhood Chain from NLYRA's own node') before the em-dash list of returned data. Every clause earns its place, especially since there is no output schema to document the returns elsewhere.

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 zero-parameter, no-output-schema dashboard tool, the description adequately covers what an agent gets back by enumerating the surfaced metrics and the Risk Level annotation. It is complete enough to call correctly, though it could state freshness/refresh expectations for a 'live' feed.

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?

The tool takes zero parameters, so there is no parameter semantics to document — the rubric baseline for 0 params is 4. The description's enumeration of return fields is useful but relates to output, not inputs, and no output schema exists.

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 uses a concrete verb ('live read') plus a specific resource ('Robinhood Chain') and enumerates exactly what the tool surfaces: TPS, hourly volume, biggest movers, most traded tokens, newest launches, each with a Risk Level. This scope clearly sets it apart from the token-scoped siblings (check_token_risk, find_token) and trade-prep siblings, though it never names an alternative explicitly.

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?

There is no explicit when-to-use or when-not-to-use statement, but the enumerated market-wide content strongly implies the use case (a market snapshot rather than per-token or trade actions), which contrasts implicitly with the siblings. Guidance is inferable but not stated.

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 the safety profile (readOnlyHint, non-destructive), and the description adds traits those annotations cannot convey: the 30-minute link expiry, the non-custodial escrow model where only the user's wallet can stop or withdraw, the conditional unsigned-transaction return, and the risk-gate refusal behavior. That is substantial behavioral 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-loaded with the core action and output, and every clause carries information (outputs, custody model, refusal condition). It is dense in a single marathon sentence, which slightly hurts scanability, but there is 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?

There is no output schema, so the description must describe returns — and it does, covering both the signing link and the conditional raw transaction. Together with custody, expiry, and refusal behavior, an agent has everything needed to call it correctly.

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?

With 75% schema coverage and a self-documenting enum, the schema does much of the work, but the description still adds meaning: token must come from list_bot_presets, budget_usd is the ETH allocation in dollars, and supplying wallet is what triggers the raw transaction to be returned.

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?

Names a specific verb ('prepares') and resource ('ETH-funded spot grid or infinity grid bot'), and scopes it to a token drawn from list_bot_presets. It also states what the call produces (a signing link, and optionally an unsigned transaction), which separates it cleanly from prepare_trade and quote_trade.

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 routes the agent to list_bot_presets for valid tokens and to the risk gate for token eligibility, giving clear context for when the call will succeed. However, it never states when to prefer a different sibling (e.g. prepare_trade for a one-off swap) or what to do when the risk gate refuses a bot.

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?

Goes well beyond the annotations by disclosing the two return artifacts (a 30-minute signing link on nlyra.xyz, and ~5-minute unsigned transactions when a wallet is supplied), the non-custodial guarantee, and the risk-gate behavior. readOnlyHint=true is consistent with a prepare-only, non-executing tool, so nothing is contradicted.

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 core action and enumerates the two return modes compactly as (1) and (2). The single dense paragraph is slightly run-on but every clause carries information; nothing is 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?

There is no output schema, so the description correctly supplies the return shape and validity windows, plus the non-custodial and risk-gate caveats. It leaves the semantics of unit/slippage to the schema, which is acceptable at 71% coverage.

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 71%, so the schema already documents unit, amount, slippage_bps, wallet and acknowledge_high_risk. The description re-states the wallet consequence (raw transactions returned) and the acknowledge_high_risk precondition, but adds no new syntax or format meaning for unit or slippage. Baseline 3 is appropriate.

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 (prepares) plus the exact resource (a buy or sell of a Robinhood Chain token via The Desk's router), and distinguishes itself from the sibling quote_trade by emphasizing that it returns a signing link and unsigned transactions rather than a price. An agent can tell what it does and what it produces without opening 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 gives conditional guidance (Critical tokens require acknowledge_high_risk=true, buys failing the sell test are refused) but never states when to pick this over siblings such as quote_trade or prepare_bot, nor that a quote is the natural precursor. Usage is only implied by the 'prepare' framing.

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 the safety profile is covered. The description adds genuine value beyond that: it confirms no order is prepared or sent, enumerates the returned fields, and discloses per-token quote-asset variation (ETH for most, USDG for some), which is a real behavioral quirk.

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?

Two dense sentences, purpose front-loaded in the first clause, mechanics second. Nothing is padded or repeated from the schema, and the closing sentence carries the buy/sell asset nuance.

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?

There is no output schema, yet the description enumerates the return contents (expected amount, price impact, fee, Risk Level) and clarifies the non-executing nature, so an agent knows both what it gets and what it will not trigger. Combined with annotations covering the safety profile, nothing material 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 moderate (60%), with side and token carrying no descriptions. The description compensates by explaining what buy versus sell actually does to the pool's quote asset, which directly informs how 'side' and 'unit' should be chosen. It doesn't add numeric formatting or range semantics for 'amount' beyond the schema, but it meaningfully extends the bare enums.

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 (quote a buy or sell of a Robinhood Chain token via The Desk's router) and immediately names what it returns: expected amount, price impact, Desk fee, Risk Level. The phrase 'Nothing is prepared or sent' implicitly separates it from prepare_trade and the risk siblings, so an agent can route without opening other 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?

Clearly establishes this is a read-only preview ('Nothing is prepared or sent'), which tells the agent to use it before any execution step. It also explains the buy/sell asset direction (buys spend the pool's quote asset, sells give it back). However, it never names prepare_trade as the execution alternative or states an explicit when-not condition, so routing is inferred rather than stated.

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, so the bar is lower, and the description meaningfully adds on top: it discloses the free-tier throttle (6 scans per 10 minutes) and the exact auth mechanism (X-Api-Key header on the MCP connection). That rate-limit and auth detail is genuinely non-obvious behavioral context not present in the structured fields.

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?

Three dense sentences, front-loaded with identity and then output contents, scoping, and limits. Every sentence carries information, though the middle sentence listing detection categories is slightly list-heavy.

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 correctly carries the return-value burden by naming the verdict tiers and the flag categories an agent will receive. Combined with chain coverage, rate limits, and auth, an agent has enough to invoke and interpret it; the only real omission is which sibling to prefer.

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%, so both parameters are already documented in the schema, including the chain default and the auto-detection of Solana mints. The description adds no syntax or format detail beyond that, 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 and resource ('NERON's contract scanner') and enumerates the concrete outputs it produces (verdict, flags, taxes, honeypot simulation, owner powers, liquidity, holders), so an agent knows exactly what it returns. It does not, however, distinguish itself from the overlapping siblings check_token_risk and check_tokens_risk, which is a real ambiguity.

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 useful operating context – 'Robinhood Chain by default; also Solana and 15 more EVM chains' – and discloses the rate limit and how to lift it, but never says when to choose this tool over check_token_risk or check_tokens_risk. Usage is implied rather than routed.

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=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so safety is covered. The description adds two genuinely useful behavioral notes beyond the schema: 'Public on-chain data only' (data provenance) and that following the money is 'slower'. It does not address rate limits or result size.

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, dense sentence that front-loads the tool's identity and then lists output categories — little waste. The enumeration of return contents is slightly long, but every clause maps to a distinct piece of information an agent would want before calling it.

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?

There is no output schema, so the description usefully compensates by enumerating the fields it returns. For a two-parameter, read-only, fully-annotated tool this is close to complete; only pagination/response-shape limits and the depth/format of the 'flags' are left unstated.

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 both parameters have their own schema descriptions (address pattern, follow_money semantics), so the baseline is 3. The description's 'follows the money one or two hops' mirrors rather than extends the schema's 'up and down two hops (slower)' wording, adding no new detail.

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?

Names a specific verb+resource ('wallet x-ray on Robinhood Chain') and then enumerates what it yields: wallet type, ETH/token holdings, Desk P&L, funders, ETH outflows, and flags. This is clearly differentiated from siblings like check_token_risk, get_price_history, or scan_contract, which operate on tokens/contracts rather than a wallet's profile and flow history.

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?

The description implies usage (profile a wallet, optionally trace funding) but never states when to pick this over an alternative or what preconditions apply. Since no sibling performs wallet-level analysis, the omission is less costly, but the agent gets no explicit routing guidance.

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