Gale Finance

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

Annotations already declare read-only, idempotent, closed-world and non-destructive behavior, so the description's added value is the fallback semantics: when no pair page exists it returns each asset's own metrics side by side and explicitly flags that pair figures are unpublished. It also discloses that pairs resolve in either order and that the cited page's A/B labels are preserved, which prevents label confusion. No rate limits or latency notes, but that is minor here.

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 the mode options, then the fallback, then an example. Dense but every sentence carries information; the embedded quoting of horizon values is slightly awkward but not wasteful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description need not explain return shapes, and it covers the remaining ambiguity an agent would face: mode selection, argument order, and the degraded no-pair-page path. Nothing needed to invoke this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning: it enumerates the accepted horizon values with their default and explains that asset_a/asset_b order is irrelevant and label order follows the source page. That goes beyond the schema's terse "First asset / Second asset" wording.

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 ("Compare two assets") plus the data source (Gale Finance's published pair pages) and the three comparison modes. It is clearly distinguishable from siblings like get_risk_return_metrics (single asset) or rank_assets_by_metric (ranking) without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context for each mode (rolling 1Y default, calendar year via horizon "2024", long-term scorecard via "long_term") and a concrete example query that shows the intended use. It does not explicitly name sibling alternatives or say when to prefer them, which keeps it below a 5.

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

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds useful scope information (what each result contains, browsing-all mode via omitted query), but says nothing about result volume, rate limits, or pagination semantics beyond the cursor parameter.

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 plus a concrete example, with the core capability and return shape front-loaded and 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?

An output schema exists, so return values need not be detailed, and the description still sketches the result categories. The remaining gap is minor guidance on how much a single page returns relative to cursor continuation.

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% with per-parameter descriptions, so the baseline is 3. The description adds value by explaining the omit-query behavior for listing everything, which clarifies the otherwise optional query parameter beyond the schema's own wording.

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?

Uses a specific verb and resource ("Search the assets Gale Finance covers") and enumerates the returned artifacts: asset page, pair comparisons, calendar-year pages, long-term scorecards. The "Do you cover Hyperliquid?" example makes the discovery role unmistakable, distinguishing it from siblings like compare_assets or rank_assets_by_metric.

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 states the two usage modes: pass a ticker/name to search, or omit the query to page through all coverage. It does not name sibling alternatives or say when to prefer them, so it stops short of a 5.

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

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds useful context beyond them: the numbers are 'Gale Finance's published' figures sourced from a compare page, implying pre-computed third-party data rather than live computation. It does not mention staleness, update cadence, or behavior for unknown assets.

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 naming the resource and scope, followed by a short usage example. The long metric enumeration partially duplicates what the output schema already conveys and could be trimmed, but it reads cleanly 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?

The tool is simple in inputs (one required identifier) and has an output schema, so the description need not explain return values, and it nonetheless names the metric set. Complete enough to call correctly; the only real omission is sibling disambiguation against get_risk_return_metrics.

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 required parameter with 100% schema description coverage that already lists accepted forms (ticker, name, alias with examples like 'BTC', 'silver'). The description adds no further meaning about accepted identifiers, ambiguity resolution, or failure behavior for unresolved assets, so the schema does all the work.

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 specific verb+resource ('published downside risk for one asset') and enumerates the exact metric family: 5% daily VaR, expected shortfall, skew, excess kurtosis, drawdown episodes, 1Y max drawdown, best/worst day. It does not explicitly differentiate itself from the overlapping sibling get_risk_return_metrics, so the boundary between the two is left to inference.

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, mainly through the example question 'What are the tail risks for bitcoin?' There is no statement of when to prefer this over get_risk_return_metrics or compare_assets, and no exclusions or prerequisites, so an agent must guess at the sibling boundary.

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, closed-world and non-destructive, so the safety profile is covered. The description adds genuinely new behavior: results carry a one-line method note and a canonical Gale page to cite, and it explicitly excludes raw prices. It says nothing about behavior when an asset is unknown, which is the remaining 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?

Front-loaded with the metric set and scope, followed by the citation detail, example, and exclusion — every element is relevant. It runs slightly long and the example is a nice-to-have rather than essential, but nothing 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?

With an output schema present, return values needn't be explained, and the description covers asset scope, both windows, metric selection, and the no-prices boundary. Only the unknown-asset or ambiguity path (handled presumably by find_assets) is left implicit.

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 schema already explains asset, window enum, and the metrics default list. The description's window and metrics phrasing largely restates those schema descriptions; the added value is mainly confirming the long window means 5Y or since inception, which the schema also states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource set — published return, CAGR, volatility, Sharpe, Sortino and max drawdown for a single asset — and constrains scope to computed metrics on two windows. An agent can distinguish it from get_downside_risk or compare_assets without opening a 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 example question ('What's the Sortino ratio of gold?') and the 'Computed metrics only; no prices' line give a clear sense of when this tool applies and where its boundary lies. It stops short of naming siblings as alternatives, so it doesn't fully route between this, get_downside_risk, and compare_assets.

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

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds that each row carries its value, window dates, and Gale page, but that return-content detail is largely duplicated by the output schema. No mention of tie-breaking or cross-type ranking 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?

Three compact sentences, front-loaded with the core operation before the row-content and example details. The metric parenthetical is dense but earns its place; the example supports usage without padding.

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 5-parameter, read-only ranking tool with a full output schema and rich annotations, the description covers purpose, metric vocabulary, and output shape sufficiently. It leaves minor gaps around ranking ties and whether results span all asset types by default, but nothing essential to calling it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description enumerates the canonical metric names (return, cagr, volatility, sharpe, sortino, max_drawdown, var_5, es_5, skew, excess_kurtosis) that the schema's free-string metric field only partially hints at. That enumeration materially reduces invalid-input risk beyond what the schema 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 (rank) and resource (assets Gale Finance covers) plus the metric dimension and optional asset-type filter, so the operation is unmistakable. It does not explicitly differentiate itself from siblings like compare_assets or get_risk_return_metrics, which keeps it just below 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?

The worked example ('Which crypto had the best Sharpe last year?') gives a concrete scenario that clarifies when to reach for this tool over a raw metrics lookup. It gives no explicit exclusions or naming of the sibling alternatives, so it stops short of full routing guidance.

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