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

Annotations already establish read-only, idempotent, non-destructive, and open-world behavior. The description adds valuable behavioral context beyond those annotations: aligned observation dates, local currencies, inclusion of period returns, actual dates, source URLs, adjustment basis, and individual failures. This gives the agent a strong sense of what the tool returns and its limitations.

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 compact and front-loaded. The first sentence states the core purpose, followed by an example, output contents, limitations, and parameter guidance. Every sentence earns its place without redundancy.

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 tool with an output schema and rich annotations, the description covers the essential user-facing behavior: symbol count, period vs. exact-date selection, output contents, and explicit non-goals. An agent has enough information to select and 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 coverage is 50%: start and end are documented in the schema, while symbols and period rely on types/enums. The description adds useful context by stating the 2–6 symbol range and advising start/end for an exact window instead of a period. It does not fully compensate for the period parameter semantics, but the enum values are largely self-explanatory.

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 starts with a specific verb and resource: 'Compare 2–6 distinct symbols over aligned observation dates in their local currencies.' This clearly identifies what the tool does and distinguishes it from sibling tools like search_markets or market_overview. The example symbols further reinforce the intended use case.

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 clearly implies the tool is for multi-asset comparisons and explicitly excludes FX conversion and trading advice. It also gives clear directional guidance on choosing an exact start/end window instead of a preset period. However, it does not explicitly name alternative tools or state when not to use this tool in favor of a sibling.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the description only adds 'Read-only; not a recommendation.' This is a useful disclaimer but does not reveal additional behavioral traits such as data recency, source, or refresh behavior. No contradiction with annotations exists.

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, purposeful lines. The core resource and output are front-loaded, and the disclaimer is kept separate. 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 read-only overview tool with one optional enum parameter, an output schema, and rich annotations, the description covers purpose, scope, and a caution. Nothing essential for an agent to select and 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?

The input schema has 0% description coverage, but the only parameter is a self-explanatory enum with a default. The phrase 'period returns' hints that the period parameter controls the return horizon, adding some meaning beyond the schema, though it does not explain each enum value or default behavior in detail.

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

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

States a specific action and resource: 'Snapshot of major indexes, rates, dollar, gold, oil, BTC/ETH and EURUSD with period returns.' It clearly identifies the broad macro-market scope, which distinguishes it from siblings like search_markets, research_asset, and compare_assets that target narrower or comparative queries.

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 this is for a quick, broad market overview, but it does not explicitly say when to choose this tool over alternatives such as research_asset or compare_assets. There are no exclusions or when-not-to-use conditions, so the guidance is mostly inferred rather than stated.

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

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds useful context: content boundaries ('source URLs and data limitations, not financial statements or full articles') and data granularity ('daily bars, or weekly bars for five years'). No contradiction with 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?

Four sentences, purpose first, with no filler. Examples, usage guidance, data limitations, and parameter advice are packed into a compact, scannable block that earns each sentence.

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 a modest parameter count, the description covers symbol format, date/period alternatives, data scope, and a search hint. Minor omissions like the 3mo default and the required flag are already handled by the schema, so nothing critical 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?

With only 50% schema coverage, the description compensates by giving concrete symbol format examples and explaining that start/end replace period for exact windows. It clarifies date format (YYYY-MM-DD) and that the two dates are used together, though it doesn't enumerate period values except the five-year behavior.

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?

Description opens with 'Research one Yahoo Finance symbol with dated prices, performance, history and news links' – a specific verb and resource. The singular 'one symbol' scope and examples distinguish it from compare_assets and market_overview, while naming search_markets for discovery.

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

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

Gives explicit guidance: use search_markets first for unfamiliar symbols, and use start/end for exact windows instead of period. It doesn't explicitly contrast when to prefer compare_assets or market_overview, but the 'one symbol' framing provides implied context.

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 a safe, read-only, idempotent profile, and the description adds meaningful behavior by disclosing that the tool returns headlines rather than article text and that the links are dated. This is consistent with openWorldHint (free-text queries may return world entities) and contradicts nothing.

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 sentences with no wasted words: the first establishes purpose, the second adds examples and an output limitation, and the third explains downstream usage. Key scoping and behavioral information is front-loaded.

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?

Given the annotations cover the safety profile and an output schema exists, the description supplies everything needed to invoke the tool correctly: what inputs look like, what outputs contain (headlines, not text), and how to use the results with sibling tools. No essential information for 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 50%: limit is fully documented with default, range, and meaning, but query has no schema description. The description compensates for query by providing concrete examples of acceptable values, yet it does not add any explanation of limit beyond what the schema already states, so the value added over structured data 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 states a specific verb ('Find'), a clear resource ('ticker symbols and dated news links'), and a well-scoped subject ('a company, asset, sector or market topic'). Concrete examples like 'Nvidia' and 'inflation' make the input space unambiguous, and the final sentence positions this tool as the discovery step feeding research_asset/compare_assets.

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 explicit usage context by instructing the agent to use the exact returned symbol in research_asset or compare_assets, implying a clear before/after workflow. It does not, however, address when to prefer market_overview, so exclusion guidance for one sibling is missing.

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