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

No annotations are provided, so the description carries the full burden. It discloses the return shape (a comparison table with defined columns), which is useful, but says nothing about whether tickers must exist, how invalid tickers are handled, or any rate/permission constraints. For a low-risk read-only lookup this is adequate but not rich.

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 short paragraphs with zero waste: the output contents are front-loaded, then the usage rule and the alternative. 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?

An output schema exists, so the description needn't explain return values, yet it helpfully previews the table columns. Combined with the clear usage routing, an agent has everything needed to invoke it correctly; only edge-case behavior (invalid/missing tickers) 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 description coverage is 100% and the single 'tickers' array parameter is documented in the schema with a concrete example (['SPY','QQQ','VTI','SCHD']). The description adds no format or cardinality guidance beyond what the schema already provides, so the baseline 3 applies.

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

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

States a specific verb ('Compare') and resource ('ETFs'), and enumerates the exact output fields (name, category, AUM, expense ratio, dividend yield, returns), so the agent knows what it gets back. It is clearly distinguishable from the sibling etf_info, which it explicitly contrasts.

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 an explicit trigger ('whenever the user mentions more than one ETF') and names the alternative it replaces ('one call instead of several etf_info calls'), with the added rationale that the result is already tabular. Nothing is left 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?

With no annotations, the description carries the full behavioral burden. It does disclose that only 'top' holdings are returned with weights, implying a truncated result set, which is useful scoping context. But it never quantifies 'top', states data freshness, or notes any auth/rate constraints.

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 tight sentence with the key output (weights) front-loaded alongside the resource. No filler or redundant 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 simple one-parameter read tool with an output schema present, return-shape explanation is unnecessary. The only real gap is the undefined size of the 'top' list, which mildly affects expectations but not invocation correctness.

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% for the single ticker parameter, so the schema already documents the argument including an example ('SPY'). The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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

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

States a specific verb (Return) and resource (top holdings of an ETF) plus the payload (portfolio weight percentages). However, it does not distinguish itself from siblings like etf_info or find_etfs_holding_stock, leaving the agent to infer the boundary.

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 etf_info for broader fund data or find_etfs_holding_stock for the reverse lookup. The agent must infer the appropriate 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?

No annotations are supplied, so the description carries the full behavioral burden. It implies a pure read operation and lists what comes back, but never states read-only status, auth requirements, rate limits, or behavior for an unknown ticker. Adequate for a trivial one-param lookup, but thin for a tool with zero annotation coverage.

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 the primary purpose front-loaded and the routing rule appended. Minor waste: enumerating the returned fields duplicates what the output schema already declares.

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 one required, fully documented parameter and a companion output schema, the description supplies everything needed to select and call the tool correctly. Only the absence of any error/permission context keeps it short of a 5.

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 (ticker) and schema coverage is 100%, with the schema already supplying the 'SPY'/'QQQ' example. The description adds nothing beyond the schema, 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?

Specific verb ('Return') plus resource ('metadata for a single ETF') and an explicit enumeration of the returned fields (name, category, AUM, expense ratio, NAV, trailing returns). It is immediately distinguishable from the sibling compare_etfs, which is named 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?

The second sentence gives an explicit when-not rule: for two or more ETFs, use compare_etfs instead, with the rationale (it returns one table). This is a clear alternative routing rule rather than implied usage.

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?

With no annotations, the description carries the full burden and does meaningful work: it discloses the default universe size (~365 ETFs), that results are sorted by weight descending, and that coverage is limited to 'disclosed top holdings' (i.e., partial data). It omits failure modes such as what happens for an unknown ticker or an empty result set, so it stops short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, zero filler, with the core purpose and the sorting/universe semantics front-loaded before the sibling routing at the end.

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 explained. Between the description's scope, sorting, universe size, and explicit alternative, plus a fully covered parameter schema, an agent has everything needed to select and 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 100%, so the schema already documents all three parameters and the baseline is 3. The description adds useful semantic context beyond the schema by stating the default universe is ~365 ETFs and that a custom list substitutes for it, clarifying the intent of custom_etf_universe.

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 ('Reverse-lookup: find ETFs that hold a given stock') plus the scope of the lookup ('disclosed top holdings'), which immediately separates it from etf_holdings and search_etfs.

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 names the alternative sibling and the condition that selects it: 'For a version that also reports each ETF's expense ratio and size, use stock_exposure_summary.' This is exactly the when/when-not routing an agent needs.

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?

No annotations are provided, so the description carries the behavioral burden. It discloses scope (stocks and ETFs) and a filtering lever, but says nothing about ambiguous multi-match results, ranking, or the fact that this is a side-effect-free read (though the output schema covers the 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?

Three short sentences, front-loaded with the core action, then the when-to-call rule, then the coverage caveat. Nothing is wasted and no sentence restates the title or 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?

With an output schema present and all three parameters documented in the schema, the description supplies the essential entry-point guidance. The only gap is behavior on ambiguous or no-match queries, which is minor for a lookup 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 coverage is 100%, so the baseline is 3, but the description adds intent beyond the schema by explaining why one would set asset_type='stock' — to exclude funds from results. That is real semantic value on top of the schema's mechanical enum listing.

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 precise verb and resource — resolve a company or fund name to its ticker symbol — so the transformation is unambiguous. It also declares coverage (stocks and ETFs), which separates it from the ETF-only siblings like etf_info and search_etfs.

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 an explicit trigger: 'Call this first whenever the user names a company instead of giving a ticker,' with a concrete example (Nvidia → NVDA). It does not state when-not-to-use or name a sibling alternative, 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?

With no annotations, the description carries the full behavioral burden. It discloses the data source and that results include ticker, name, and exchange, but says nothing about rate limits, failure/empty-result behavior, or whether results are cached or live. Adequate context for a simple read search, but not rich.

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, zero waste, front-loaded with purpose, then return, then routing. 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?

An output schema exists, so return values need not be spelled out further, and the description already covers purpose, discovery role, and the sibling alternative. Nothing an agent needs to invoke it correctly is missing.

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

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

Schema coverage is 100%, so both parameters are already documented, including the query examples ('semiconductor', 'dividend') that the description echoes. The description adds no syntax or format guidance beyond the schema, 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 ('Search for ETFs') plus the scope of the search (name, theme, or category) and the backing source (Yahoo Finance). It also summarizes the return (matching tickers with names and exchanges), so an agent can distinguish it from siblings like etf_info without opening 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?

Names the downstream consumers (etf_info, compare_etfs, etf_holdings, find_etfs_holding_stock), which tells the agent this is a discovery entry point. It also gives an explicit when-not with the alternative: use lookup_symbol to resolve a stock or company name instead.

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?

No annotations are provided, so the description carries the full behavioral burden. It conveys the shape of the result (per-fund weight, expense ratio, AUM), which is useful, but says nothing about ordering of results, what happens with an unknown ticker, or that this is a read-only lookup. With an output schema present, the return-value gap is forgivable, but the behavioral coverage is thin for an unannotated tool.

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 short sentences, front-loaded with the core action and outputs. The second sentence is partly redundant with the first but earns its place by naming the decision it supports. 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?

With a full output schema and 100% parameter coverage, the description need not explain return values or argument formats, and it correctly stays brief. The remaining omission is sibling differentiation in a crowded ETF-tool family, which is a meaningful but bounded 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%: both 'stock' (ticker or name, with examples) and 'limit' (range and default) are fully documented in the schema. The description adds only the meaning of the returned metrics, not new parameter semantics, 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 ('find the ETFs that give exposure to a stock') and enumerates the returned metrics (weight, expense ratio, AUM), so the agent knows exactly what this produces. It does not, however, differentiate itself from the near-identical sibling find_etfs_holding_stock or from compare_etfs, which leaves a real disambiguation gap.

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 framing question 'what is the cheapest / largest ETF for exposure to X?' implies a use case and hints that this tool is for comparison-style selection. But it never states when to prefer it over find_etfs_holding_stock or compare_etfs, nor any exclusions, so routing must be inferred.

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