OwlChart

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the bar is lower. The description usefully adds the 30-symbol cap and per-member ownership scope, but says nothing about duplicate handling, error behavior when the cap is exceeded, or why the operation is non-idempotent as the annotation claims.

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 operation, then the resource, examples, and limit. No filler, nothing to trim.

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 one-parameter add tool with no output schema, the description covers the action, the target, accepted value shape, and the hard limit. Only marginal gaps remain: duplicate behavior and what happens at/over the 30 limit.

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 0%, so the schema only conveys that 'symbols' is a string array. The description compensates by defining what a symbol is (a market ticker), giving concrete examples, and stating the 30-item ceiling that the schema does not encode.

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 ('Adds') plus resource ('markets ... to this member's own watchlist') and scopes it with examples (BTC, WLFI, AAPL). The verb contrast with remove_from_watchlist and get_watchlist makes it unambiguous which operation this is 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?

The description implies its context (curating one's own watchlist) and supplies a real usage constraint ('up to 30'), but names no alternatives and gives no explicit when/when-not guidance relative to get_watchlist or remove_from_watchlist.

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?

The description discloses the key state change that explains the readOnlyHint=false annotation: it 'marks them read'. It also conveys incremental semantics ('since the last check'), which aligns with idempotentHint=true. It does not mention any permission/auth requirement or whether the read-marking is reversible, so it is strong but not exhaustive.

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 with a specific action, scope, and side effect, front-loaded with the return value. Nothing is redundant or padded.

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 parameters, no output schema, and annotations covering the safety profile, the description carries what an agent needs: what is returned, the time window, and the side effect. A brief note on the alert payload or on how it differs from list_alerts would close the remaining 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?

The tool takes zero parameters, so the baseline is 4; there is no parameter surface for the description to compensate for.

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 this member's alerts that fired') plus scope ('since the last check'), which is concrete enough to act on. However it does not differentiate itself from the sibling list_alerts, so an agent must guess which of the two alert-listing tools fits.

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 phrase 'since the last check' implies the polling/incremental use case, which is useful implied guidance. But it never names list_alerts or states when to prefer one over the other, and gives no prerequisites or 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 only cover the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=false); the description adds the operationally important facts: one-shot behavior, a per-member cap of 10 active alerts, one-minute evaluation cadence, and outbound webhook delivery. The non-idempotent annotation is corroborated by the 'one-shot' semantics rather than 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?

The purpose and cadence are front-loaded, and the dense type-by-type breakdown each earns its place by defining a distinct trigger. It is a long single block, but there is little redundant wording and no marketing 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 no output schema, the description still tells the agent where results appear (check_alerts), how delivery works (webhook), the quota, and the one-shot nature. For a 5-parameter mutation tool, an agent has everything needed to invoke 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?

Schema coverage is only 60%, and the description compensates heavily on the most consequential parameter, threshold: dollars for price alerts, percent for oi_change/funding_extreme, a signed value (negative for a drop) for oi_change, and no threshold at all for magnet_hit. It also adds a constraint missing from the schema (etf_flip coin must be BTC or ETH), though the 'note' parameter remains undocumented in both places.

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 ('Sets an alert on OwlChart data') plus a behavioral detail ('checked every minute'), and the type enumeration distinguishes it from the sibling read/manage tools check_alerts, list_alerts and delete_alert. An agent can identify the tool's role 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?

The description gives clear context for when each alert type applies, what fires it, and where the result surfaces ('shows in check_alerts'), which effectively routes an agent to the creation flow versus the inspection flow. It does not, however, state exclusions or prerequisites explicitly (e.g. when to prefer list_alerts or delete_alert, or account requirements).

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 destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds the id provenance and the member-scoped ownership constraint, but says nothing about irreversibility, failure behavior for an unknown id, or effects on triggered alerts.

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 short sentence that front-loads the action and its key; every clause earns its place with 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 one-parameter deletion tool whose annotations already convey destructiveness and idempotency, this is close to sufficient. The main remaining gap is what happens on an invalid or already-deleted id, which matters more here because idempotency is asserted but not explained.

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 0%, so the schema gives no semantics. The description partially compensates by telling the agent the id is an alert id obtained from list_alerts and is member-scoped, but it adds no format details (UUID vs numeric) or constraints.

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 ('Deletes ... alerts') and its lookup key ('by its id'), which cleanly separates it from create_alert and list_alerts. It does not name those siblings explicitly, so it falls short of full differentiation.

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 parenthetical '(from list_alerts)' gives an implicit workflow hint about where the id comes from, which is real usage guidance. However, there is no explicit when-to-use vs when-not, no mention of confirmation requirements, and no exclusivity guidance against alternatives.

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 and openWorldHint=true, so the safety and scope profile is covered. The description adds useful context that results carry dates and come from a 'live' tracker (implying freshness), but it says nothing about result volume, pagination, or update cadence beyond the word 'live'.

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, front-loaded with the subject matter and backed by a parenthetical of concrete examples. No filler or 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?

For a no-argument, no-output-schema news tool the description covers what the agent needs: source, topic scope, named entities, and the presence of dates. It would be complete at 5 if it hinted at how much content is returned or how recent 'latest' is.

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, which is the baseline-4 case per the rubric. The description correctly signals that no filtering is required, and nothing in the schema needs compensating for.

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 (crypto market structure law and regulators) and enumerates the concrete content covered: the CLARITY Act and related bills, SEC and CFTC items, with dates. This clearly distinguishes it from every sibling, all of which return market/pricing data (flows, funding, liquidations, orderbook) rather than regulatory news.

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 content scope — call this for regulatory/legislative updates — but the description never states when to use it versus alternatives, nor any exclusions. With no competing regulatory sibling the ambiguity is low, so 3 is fair rather than a penalty.

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?

readOnlyHint=true and openWorldHint=true already tell the agent this is a safe, open-world read, so the bar is lower. The description usefully adds that results are aggregated from 'three raw sources' and includes an interpretive 'verdict', but says nothing about freshness semantics, rate limits, or result granularity.

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 resource and stays compact. The ellipsis, nested quotes and parenthetical fund examples are slightly informal but do not waste 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 must describe returns, and it does sketch them (fund-by-fund flows, recent days, a verdict). However, 'recent days' is imprecise and nothing is said about output shape or time coverage, leaving gaps for a data-retrieval tool.

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%, so the description must carry the parameter meaning; it partly does by stating 'Bitcoin or Ethereum', which maps to the btc/eth enum. It does not mention the default of btc, and with a single enum param the added value is modest.

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 resource (Bitcoin or Ethereum spot ETF flows, fund by fund) and even cites concrete funds (BlackRock IBIT/ETHA, Fidelity, Grayscale), so an agent immediately knows what it retrieves. It is clear but doesn't explicitly position itself against siblings; the distinct resource alone carries the differentiation.

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 statement of when to use this tool versus alternatives, no prerequisites, and no exclusions. The description only says what data exists, leaving the agent to infer that it should call this for ETF-flow questions rather than get_price_history or get_market_radar.

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 and openWorldHint, so the safety profile is covered. The description adds genuine behavioral context beyond that: the data spans every exchange OwlChart reads, and the sign convention is decoded ('Positive means longs pay shorts'), which is essential for interpreting results.

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 with the resource front-loaded and no filler; the sign convention follows naturally. It is efficient, though slightly terse given what remains undocumented.

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 read-only tool with one parameter and no output schema, the description covers what is returned (per-exchange rates) and how to read it. It omits freshness/update cadence and the coin identifier format, which is the main residual 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 0%, so the description carries full responsibility for the single parameter, yet it only implies that 'coin' exists and never states the expected format (ticker symbol vs. full name). An agent must guess the identifier convention.

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 ('Perpetual funding rates for a coin') plus the scope of coverage ('on every exchange OwlChart reads'). It distinguishes itself from rate-adjacent siblings like get_open_interest and get_liquidations, 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 when-to-use or when-not-to-use guidance, and no sibling is named as an alternative. The phrase 'straight from the exchanges' hints at live source data but stops short of any real routing advice.

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 and openWorldHint=true, so the safety profile is covered. The description adds genuine provenance ('recorded by OwlChart from the exchanges' public feeds') and disambiguates 'actually liquidated' from hypothesized levels, but says nothing about staleness, rate limits, or granularity.

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 with no filler. It is efficient, though its brevity is also part of why parameter detail is missing.

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 read-only, two-parameter tool with no output schema, the description covers the semantic meaning of the return (realized liquidations by side and time window). However, the complete absence of parameter documentation and any note on data granularity or limits leaves it only marginally sufficient.

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 0%, so the description carries the burden. It only conceptually gestures at 'a coin' and 'over the last hours' without explaining the coin identifier format (symbol vs pair vs id) or that hours defaults to 24 and caps at 168. This leaves real gaps for a 2-param tool.

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?

Specific verb+resource: it fetches long/short positions 'actually liquidated' for a coin over a time window, and names the source. This is clearly distinct from siblings like get_funding_rates or get_open_interest, though the description never explicitly contrasts them.

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 guidance, no alternatives, no exclusions. The context of liquidations is implied by the topic, but an agent gets no help deciding between this and related derivatives tools such as get_open_interest or get_funding_rates.

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 carry readOnlyHint and openWorldHint, so the safety profile is covered. The description goes further by scoping the domain to crypto coins and disclosing that results include 'the model's measured hit rate' plus that all OwlChart charts share one consensus answer, which is genuine reliability/consistency context beyond the annotations. Freshness cadence and rate limits remain unstated.

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?

It is a single dense sentence, but because there is no output schema the enumeration of returned fields earns its place and the consensus answer is front-loaded as instructed. It reads as a run-on mixing consensus and heatmap concerns, which slightly hurts scannability.

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 must convey the return shape, and it does so thoroughly: consensus headline, magnets above/below, net pull, whale bids/asks, open interest, long/short split, RSI, TBO trend, hit rate. Combined with read-only annotations, an agent has enough to call it correctly; only update cadence is unaddressed.

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% for the single 'coin' parameter, so the baseline of 3 applies. The description adds only slightly more than the schema by listing extra example tickers and restricting to crypto, but contributes no format or validation detail beyond what the schema already says.

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 two concrete deliverables: the OwlChart consensus direction and the surrounding liquidation levels ('nearest liquidity magnet above and below, net pull direction'). This clearly differentiates it from data-only siblings like get_liquidations or get_open_interest, though the run-on enumeration is closer to an output inventory than a crisp verb+resource statement. It never names a sibling directly.

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: 'around the current price' and 'Crypto coins only (BTC, ETH, SOL, WLFI ...)' gesture at when it applies, and 'lead with consensus.headline' hints at how to read the result. There is no explicit when-to-use vs get_liquidations/get_open_interest guidance and no exclusions. Adequate but with a clear gap.

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 and openWorldHint=true, so safety is covered. The description adds genuine value by disclosing the fixed coin set and the three returned dimensions, which matters with no output schema. It does not mention freshness, caching, or whether the list can be configured.

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 sentence, front-loaded with the scope ('major coins at once') followed by the payoff (coins and fields). No filler whatsoever.

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 no-parameter snapshot tool with annotations covering the safety profile and no output schema, the description tells the agent what it gets and for which assets. Only minor gaps remain (data freshness, whether the coin set is fixed vs. configurable), which are not blocking.

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?

Zero parameters, so per the rubric the baseline is 4. The description correctly conveys that the tool is parameterless and operates on a fixed coin list, which is the only semantic an agent needs here.

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 ('read') and resource ('major coins at once'), and enumerates both the covered coins and the returned fields (Owl Score, price, verdict). It is clearly distinct from per-coin sibling get_owl_score, though it never names that sibling 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?

'A quick read' implies a snapshot/overview use case versus the deeper per-coin tools in the sibling list, but there is no explicit when-to-use / when-not-to-use statement or named alternative, leaving the routing to inference.

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 and openWorldHint=true, so the safety profile is covered. The description usefully adds the temporal window (last day) and discloses the data provenance (minted/burned read from the contracts), but says nothing about refresh cadence, latency, or any coverage caveats for an aggregated snapshot.

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 with the scope constraint ('over the last day') front-loaded ahead of the content list. It is dense but each listed source earns its place; only the trailing open-interest clause reads as slightly tacked on.

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 and no parameters, the enumeration of returned content in the description is what carries the tool. It is nearly complete, though it omits the form/units of the returned numbers and does not flag that overlapping siblings exist.

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 and schema coverage is 100%, so baseline 4 applies. There is nothing for the description to clarify about inputs.

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 gives a concrete resource (money flows over the last day) and enumerates the specific data it aggregates: stablecoin mint/burn, tokenised gold and treasuries, ETF flows, BlackRock bitcoin, and 24h open interest change. An agent knows what this returns, but it never distinguishes itself from siblings that cover the same ground (get_etf_flows, get_open_interest, get_tokenization_overview).

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 statement of when to use this aggregate overview versus the specific siblings like get_etf_flows or get_open_interest, and no exclusions or prerequisites. The agent must infer that this is a broad daily digest rather than a drill-down.

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 declare readOnlyHint and openWorldHint, so safety is covered; the description adds real value beyond them by disclosing ordering ('newest first') and the per-item payload (source, time to the second, link, price at headline, move since), which matters because there is no output schema. It omits any pagination, result-count, or rate-limit behavior, keeping it out of the top band.

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 identity in the first clause and dense with substantive detail, though it is a single run-on sentence and the trailing 'written from OwlChart live data' is promotional filler that does not help tool selection.

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 and only 50% schema description coverage, the description carries the full burden and does so: it enumerates returned item fields, ordering, and the two filters. An agent has everything needed to decide when and how to call it.

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 only 50% — the enum parameter 'desk' has no schema description — but the description compensates by naming all enum values ('all, crypto, x, stocks') and clarifying that 'coin' is an optional filter with BTC as an example. That is more than the schema provides, so it earns above the baseline 3.

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 ('the live news wire OwlChart reads, newest first') and enumerates the exact content classes: crypto news, X accounts, stock/macro news, rule changes, chart patterns, economic calendar, Owl Journal. No sibling tool covers news, so the agent can distinguish it cleanly from quote/data tools like get_market_radar or search_markets.

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 context is clear — this is the news feed, filterable by coin and desk — and the descriptor 'market-moving X accounts' and 'next economic calendar events' tells the agent what questions it answers. It stops short of explicit when-not or named alternatives, but no competing sibling exists for this content, so the gap is minor.

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 and openWorldHint, so the safety profile is covered. The description adds useful behavioral context beyond annotations: it specifies aggregation across 13 named exchanges, a one-row-per-venue output shape, and the 24-hour change metric. It does not cover auth, rate limits, or update frequency, but for a public read-only analytics tool that is a minor gap.

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 description is a single front-loaded sentence, which is good structure. However, the parenthetical list of 13 exchanges is long and arguably unnecessary for tool selection, bloating the sentence without clear benefit to the agent.

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 read-only, single-parameter tool with no output schema, the description adequately explains the return shape and exchange coverage, and annotations carry the safety profile. It still leaves key gaps: no coin format guidance and no when-to-use context. Adequate but incomplete.

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%, so the description must compensate for the undocumented coin parameter. It only repeats 'for a coin' without specifying symbol format, case sensitivity, or examples, adding essentially no meaning beyond the parameter name itself.

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 (live open interest), scope (summed across 13 exchanges), and output granularity (one row per venue with coins, dollars, share, and 24h change). It is clearly distinct from siblings like get_funding_rates and get_liquidations, but it does not explicitly name an alternative or contrast itself with one.

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, when-not-to-use, or alternative guidance. The agent can infer it is for open interest, but the description gives no context about when this tool should be selected over related market-data tools.

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 and openWorldHint=true, covering the safety profile. The description adds that the data spans 'wired exchanges' and names specific order-book metrics, which is useful context. It does not disclose return format, refresh behavior, or rate limits, but with annotations covering the core behavioral traits, a 3 is appropriate.

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 description is a single, front-loaded sentence that efficiently lists the returned content. Every phrase earns its place, and there is no redundant or filler text.

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, single-parameter market data tool with no output schema, the description gives a good high-level summary of what the response contains: depth, walls, and imbalance across exchanges. It could do more to specify the coin identifier format or whether the data is live versus snapshot, but it is largely complete for an agent to invoke the tool 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?

Schema description coverage is 0%, so the description must compensate for the single 'coin' parameter. It only says 'for a coin' without clarifying format (ticker, symbol, contract address) or whether it must match a specific exchange convention. That is barely more than the parameter name itself, so it does not adequately cover the gap.

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 clearly states the resource: resting bids and asks for a coin, plus specific metrics (depth near price, biggest walls, buy/sell imbalance). It is not a tautology and gives an agent a precise sense of what the tool returns. However, it does not explicitly differentiate itself from sibling tools like get_liquidity_heatmap or get_market_radar, so a 4 is appropriate.

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 guidance on when to use this tool versus alternatives such as get_liquidity_heatmap or search_markets. The description only implies usage through the content it returns, leaving the agent to infer the right context. No exclusions or prerequisites are 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 readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description goes beyond that by disclosing the score's weighting model (45/55 split) and the return payload (verdict, price, RSI), which helps the agent trust and interpret results. It doesn't mention auth, rate limits, or behavior for unknown coins.

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 tight sentences with no filler; the score definition and composition are front-loaded, and the interpretive caveat is a single well-placed clause. Every sentence 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?

With no output schema, the description usefully enumerates the return fields and the score's internal weighting. However, it leaves the coin identifier format unresolved and says nothing about error behavior for invalid or unknown coins, so it is adequate but not fully self-contained for a single-parameter lookup.

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 one required parameter, 'coin', with 0% schema description coverage, so the description carries the full burden. It says only 'for a coin' and never specifies the expected identifier format (ticker symbol, CoinGecko id, or name). That ambiguity is a real invocation risk that the description fails to resolve.

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 resource ('OwlChart's 0 to 100 score for a coin') and states exactly what composes it (market regime 45%, entry signal 55%) plus the accompanying verdict, price and RSI. An agent can tell this is a proprietary composite-score lookup rather than raw market data. It stops short of explicitly contrasting itself with the sibling data feeds (get_price_history, get_funding_rates, etc.).

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: 'A reading of conditions, not a trade call' tells the agent how to interpret the output, which is a useful framing hint. But there is no statement of when to reach for this over a sibling like get_market_radar or scan_patterns, and no exclusion or prerequisite conditions.

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 and openWorldHint=true, so the safety profile is covered. The description adds value by disclosing what the response contains (candles plus last price, change over window, high, low), a behavioral trait not in the annotations, but says nothing about rate limits, pagination, or window semantics.

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 sentences, no filler, with the primary purpose front-loaded and the input-format caveat second. 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?

No output schema exists and the description compensates by summarizing the return shape. The main symbol-format ambiguity is resolved. Minor gaps remain around interval/limit semantics and window length, but nothing critical for a correct invocation 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 0%, so the description carries the full burden. It resolves the key ambiguity for `symbol` (plain ticker vs market id), which is genuinely useful; `interval` is a self-descriptive enum and `limit` is bounded 20-500 with a default in the schema, so the remaining gap is modest rather than severe.

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 combination (OHLCV candles) plus the summary payload returned, which is concrete and distinguishable from siblings like get_orderbook_depth or get_funding_rates. It does not explicitly differentiate from adjacent tools such as scan_patterns or get_market_radar, so it falls short of a 5.

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 clarifies accepted input forms (plain ticker BTC/ETH/AAPL or an id from search_markets), which is real usage guidance and routes the agent to a sibling for id resolution. However, it gives no when-to-use guidance versus alternatives like get_market_radar or scan_patterns, so usage is only implied.

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 and openWorldHint=true, so safety is covered. The description adds the data provenance ('read from the contracts'), which is useful context about freshness/source. It does not cover update cadence, coverage universe completeness, or return shape.

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?

It is a single sentence, which is efficient, but the opening rhetorical question ('How much real-world value is on-chain today') delays the actual payload and the parenthetical examples (BlackRock BUIDL, Ondo ...) add length without much selection value. Front-loading could be tighter.

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-param read tool with no output schema, the description does list the data categories covered, which is the main thing an agent needs. However, it says nothing about the response structure, units, or whether the world-market denominators are included, so the agent must discover output shape at call time.

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 the baseline is 4. The description appropriately spends no words on arguments and instead explains the data content.

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 the specific resource (on-chain tokenisation: stablecoins, tokenised treasuries/funds, gold, shares) and the framing metric (value on-chain vs. each world market). An agent can distinguish it from sibling get_crypto_regulation or get_etf_flows. The rhetorical question opening is less direct than a verb-first phrasing, but the content is clear.

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 statement of when to call this versus alternatives, no prerequisites, and no mention of any sibling. The agent must infer usage purely from the subject matter.

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 and openWorldHint=true, so the safety profile is known. The description adds meaningful behavioral context: calls are logged before the outcome then scored, and it specifies the exact metrics computed, which goes beyond annotations.

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 that front-load the core resource and follow with the metric list. No wasted words, though the second sentence is a somewhat long enumeration.

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, single-parameter tool with no output schema, the description covers what the tool returns and how the data is generated. It stops short of explaining the return shape or pending-call semantics, but the annotations and schema carry the rest.

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 100% schema coverage, the single optional 'coin' parameter is fully documented in the schema. The description's phrase 'overall and per coin' implies the coin parameter's effect but adds no format or syntax 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 description names a specific resource (OwlChart's liquidity pull model track record) and specifies the exact contents returned: hit rate, direction accuracy, 95% range, pending calls, overall and per coin. This is clearly distinguishable from siblings like get_owl_score or get_market_radar.

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 explains what the record contains but doesn't explicitly state when to use this tool versus alternatives like get_owl_score. Usage is implied for credibility checks, but there are no stated exclusions or 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=true and openWorldHint=true, so the safety profile is covered. The description adds useful context by disclosing what data is returned (live price and 24h change per market), but says nothing about auth requirements or freshness/staleness of the live prices.

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 carries the resource and the returned data with no wasted words.

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 needs to convey the return shape, and it does so at a high level (live price plus 24h change per market). For a no-arg read tool this is nearly complete, though it omits how empty watchlists behave.

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 nothing for the description to disambiguate. Baseline 4 applies since parameter semantics are trivially satisfied.

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 clear verb+resource (get this member's own watchlist) and even names the returned fields (live price and 24-hour change). It is distinguishable from the mutating siblings add_to_watchlist/remove_from_watchlist, though it does not name them 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?

No explicit when-to-use guidance or routing to alternatives. The phrase 'this member's own watchlist' implies the context but never states conditions or exclusions versus add_to_watchlist/remove_from_watchlist or search_markets.

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 and openWorldHint=false, covering the safety profile. The description adds the useful scoping detail that results include both active and recently fired alerts, but says nothing about ordering, limits, or how 'recently' is bounded.

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 with no filler. Every word (member scope, active, recently fired) carries information, and nothing is padded.

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 parameters, no output schema, and annotations covering the read-only profile, the description supplies what an agent needs: whose alerts and which subset. The only gap is the undisclosed size/ordering of the result set.

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 the baseline is 4. There is no input to describe and the description correctly does not invent any parameter semantics.

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 (Lists) and resource (alerts) with a scope qualifier ('this member's'). It distinguishes itself somewhat from create_alert/delete_alert by being a read, but it does not differentiate from the sibling check_alerts, which likely overlaps in intent.

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 by the possessive scoping ('this member's'), which hints at a personal listing. There is no explicit when-to-use or when-not-to-use guidance, and crucially no routing away from the overlapping sibling check_alerts.

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 destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact beyond that: the scope is limited to "this member's own" watchlist, implying a per-user authenticated context. It does not say what happens when a symbol is absent or whether a partial failure occurs.

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 efficient sentence with the verb and scope front-loaded and zero filler. It is terse to the point of under-specification, but nothing in it is wasted.

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?

Annotations cover the destructive/idempotent profile and there is no output schema to explain, so the definition is callable. Still missing for a destructive mutation: the identifier format for symbols, behavior when a symbol is not present, and any authorization requirement implied by "member's own."

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%, so the description carries the full burden, yet it only implies plurality via "markets." It never states whether symbols are tickers, market IDs, or slugs, nor what an empty array does. With one required undocumented parameter, this is a real gap.

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?

Specific verb ("Removes") plus resource ("markets ... watchlist"), so the action is unambiguous. It implicitly separates itself from add_to_watchlist and get_watchlist by naming the inverse and read operations' resource, but it never names a sibling 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?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as get_watchlist for inspection or add_to_watchlist for the inverse. The agent must infer the context entirely.

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 and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context about what is returned (win rates, a confluence score), but says nothing about latency, coverage limits, or how patterns are sourced.

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 core action and packs the key output details without filler. Efficient, though the clause-after-colon structure makes it slightly harder to scan than a split sentence would.

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 two-parameter read-only tool with no output schema, the description covers purpose and returns adequately, but it leaves the interval enum and symbol format unexplained. Given 0% schema description coverage, this gap matters.

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%, so the description must compensate, and it doesn't. It vaguely maps 'market' to symbol and 'timeframe' to interval, but gives no format guidance for symbol and never explains the interval enum values or the default.

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 (runs) and resource (OwlChart's pattern engine) plus the inputs (market, timeframe) and the output content (candlestick/chart patterns, historical win rates, confluence score). It is clearly distinguishable from data-fetching siblings like get_price_history or get_orderbook_depth, though it never names a sibling 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 when-to-use, when-not-to-use, or alternative routing guidance. The agent must infer that this is for pattern detection rather than raw price retrieval, but the description offers nothing about prerequisites or competing tools.

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 and openWorldHint, so safety is covered; the description adds value by disclosing the return format ('crypto_perp:bybit:BTCUSDT', 'equity:NASDAQ:AAPL') that no output schema provides. It omits ranking/ambiguity behavior for multi-match queries.

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 tight sentences: coverage first, then the return-value contract and its consumer. Nothing is repeated from the title or schema and 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 one-parameter lookup with no output schema, the description supplies the critical missing piece: the shape of the returned id. Coverage list plus id format is nearly enough; match-ranking or case-sensitivity behavior would close the remaining 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 description coverage is 100% and the single query parameter is fully documented there with examples. The description adds no syntax or matching-semantics detail (prefix vs fuzzy vs exact) beyond what the schema already states, 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 verb (Find) and resource (any instrument OwlChart covers), then enumerates the asset classes covered, which cleanly separates it from siblings like get_price_history or get_etf_flows that act on a single market type.

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 the tool as the lookup step whose output ids feed into get_price_history, giving clear downstream context. It stops short of stating when NOT to use it (e.g. when an id is already known), so no explicit 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 readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely new behavioral context: the chart is rendered inside the chat, liquidity magnets are overlaid for crypto coins, and numeric data is returned alongside the visual. It doesn't address rate limits or whether the chart is ephemeral.

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 short sentences, front-loaded with what the tool produces and ending with the usage trigger. Only mild padding in 'Also returns the numbers,' which is vague but cheap.

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 should carry the return-value burden, and 'also returns the numbers' is too vague to tell an agent what data comes back or whether it needs to render separately. For a 2-param read-only chart tool this is adequate but leaves a real 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 50% – symbol is documented but interval is not described in the schema beyond its enum. The description compensates slightly by enumerating supported market types (crypto, stocks, forex, commodities), implying flexible symbol formats, but says nothing about interval values or defaults.

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 concrete verb and resource ('Shows an interactive OwlChart candle chart inside the chat'), names supported markets, and adds the distinguishing behavior (liquidity magnets for crypto). This clearly separates it from data-only siblings like get_price_history by signaling a rendered chart artifact.

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?

'Use it when the user wants to see a chart' gives an explicit triggering condition. It stops short of naming alternatives (e.g. get_price_history for raw numbers) or stating when not to use it, so it lands at 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.