Cabrini MCP

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

No annotations are provided, so the description carries the full burden of disclosing behavioral traits. It mentions 'derived aggregates' but doesn't explain what that means. Pricing is provided, but there is no mention of read-only nature, side effects, data range limitations, or performance. More context is needed for a data retrieval 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?

The description is two sentences, highly concise, and front-loaded with the most critical information. Every word serves a purpose, and there is no extraneous content.

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?

Despite being concise, the description lacks completeness. With no output schema and no annotations, the user is left without knowing the output format (OHLCV likely), handling of missing data, restrictions on date ranges, or the effect of the 'adjusted' parameter. For a 6-parameter tool, this is insufficient.

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 parameter descriptions are already present. The description adds the list of valid intervals and notes 'derived aggregates for one ticker', which provides context. However, it does not clarify the distinction between 'date' and 'start/end' or the behavior of the 'adjusted' parameter.

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 it provides resampled OHLCV bars at specific timeframes for a single ticker, distinguishing it from sibling tools like get_pricing or query_minute_bars. The verb is implicit but clear. It could be more explicit about the action (e.g., 'Retrieve resampled OHLCV bars').

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 indicates usage for custom intraday timeframes (3,6,...240 min) and notes it's for one ticker. It mentions cost, which is relevant for usage decisions. However, it does not specify when not to use this tool (e.g., for standard minute bars use query_minute_bars) or provide clear 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?

With no annotations, the description carries full burden. It discloses a cost of $0.25 USDC, which is valuable. It also outlines the data categories included, though it could mention potential side effects or rate limits.

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?

Single, efficient sentence with no superfluous text. Every word serves a purpose.

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 3 parameters and no output schema, the description is somewhat complete but lacks detail on return structure. 'Full research brief' is vague; specifying the fields or format would improve completeness.

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% but the description adds no extra meaning to parameters. It lists data categories but doesn't link them to parameters (e.g., how 'lookback_days' affects price history). Baseline score of 3 is appropriate.

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

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

The description clearly states it provides a 'Full research brief' covering price, fundamentals, insiders, and splits for one ticker. This distinguishes it from siblings like get_bars or get_fundamentals, though it doesn't explicitly contrast 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 explicit guidance on when to use this tool vs. alternatives. The description implies it's for comprehensive data per ticker, but does not specify scenarios 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?

Only behavioral trait disclosed is cost ($0.005 USDC). No annotations provided, so description should cover read-only nature, rate limits, or side effects. It does not, leaving significant ambiguity for a tool that likely performs a read operation.

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?

Extremely concise: a single sentence that front-loads the purpose ('Company profile') and lists key fields and cost. Every word adds value.

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 a single parameter and no output schema, the description lists fields but does not specify return structure (e.g., JSON keys, pagination, error cases). It is functional but leaves the agent guessing about exact response format.

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 already describes the ticker parameter with example. Description adds no additional nuance about parameter usage or constraints. Since schema coverage is 100%, baseline 3 is appropriate.

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

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

Description clearly states it retrieves a company profile with fields like name, CIK, industry, exchange, fiscal year. It is distinct from sibling tools that focus on fundamentals, insiders, pricing, etc. However, it could be more explicit about the exact scope of 'profile'.

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 guidance on when to use versus alternatives (e.g., get_fundamentals for deeper data). No exclusions or prerequisites stated. Agent must infer usage 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?

The description only discloses pricing and optional text extraction cost. With no annotations provided, it carries the full burden but fails to mention other behavioral traits like pagination, rate limits, or error handling. The cost transparency is appreciated but insufficient for full disclosure.

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

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

The description is two sentences, front-loaded with the main purpose, and every word adds value. No fluff or irrelevant detail, making it highly concise and easy to parse.

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 6 parameters, no output schema, and no annotations, the description is too brief. It covers pricing and optional sections but does not describe the return format (e.g., list of filings with metadata, fields), pagination, or error handling. The missing output schema makes this gap more significant.

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 parameters. The description adds context for the 'sections' parameter (extracting full section text for a fee) but does not provide any new semantic information beyond what is in the schema. Baseline 3 is appropriate.

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

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

The description clearly states it provides an SEC filing index for a ticker, listing common types. It distinguishes from siblings like get_bars or get_company by focusing on regulatory filings. However, it doesn't explicitly say it returns a list or how it's structured, slightly limiting clarity.

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 guidance on when to use this tool versus alternatives. It mentions cost and optional section extraction but does not explain prerequisites or context for choosing this over other tools, leaving usage ambiguous.

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 is the sole source. It discloses the data source (SEC EDGAR) and frequency (quarterly), but lacks details on rate limits, authentication, or error handling. Adequate but minimal.

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 sentence with a cost note, efficiently conveying core purpose. It is front-loaded with key terms. Minimal but effective for its length.

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

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

With no output schema, the description does not explain the return structure. Optional parameters (metrics, dates) lack usage context. The tool has moderate complexity (4 params) and misses guidance on output.

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 defines parameters. The description adds context (quarterly, SEC EDGAR) but does not clarify optional parameters like metrics filtering. Baseline score of 3 is appropriate.

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

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

The description clearly states the tool retrieves quarterly fundamentals from SEC EDGAR, specifying data types (revenue, EPS, margins) and source. It distinguishes from siblings like get_pricing or get_stats by focusing on fundamentals.

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 mentions a cost ($0.02 USDC), implying a usage condition but does not explicitly state when to use or not. No references to alternatives or exclusions are provided.

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 provided, leaving the description to disclose behavior. Only cost is mentioned; missing rate limits, authorization, data latency, or side effects. Significant gap for a data retrieval 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?

Single sentence front-loading primary function and cost. No unnecessary 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?

Given 3 parameters (1 required), no output schema, and no annotations, the description lacks usage guidelines and behavioral details needed for an agent to reliably use the 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 100%, so baseline is 3. Description adds no further meaning beyond what schema already provides (ticker, from_date, to_date).

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?

Clearly states the tool retrieves insider transactions (Form 4) from SEC EDGAR, distinguishing it from sibling tools like get_company or get_fundamentals. The cost mention is additive but does not detract from clarity.

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 guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. The cost hint implies use when necessary, but no explicit 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?

With no annotations, the description must disclose behavior. It only says 'Free' and vague information, lacking details on side effects, authorization, or output.

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?

Very short at two sentences, no wasted words, but could provide more detail without losing conciseness.

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 parameterless tool, the description is minimal. It does not explain what 'data coverage information' entails or the return format, leaving gaps.

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?

No parameters exist, so baseline 4 applies. Description adds nothing but is not misleading.

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 'Pricing and data coverage information' which identifies the resource but does not specify the verb or distinguish from sibling tools like get_stats or query_range.

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 guidance on when to use this tool versus alternatives. Only mentions 'Free' without 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?

No annotations exist, and the description only states 'Free.' No disclosure of read-only nature, idempotency, or other behavioral traits beyond the minimal statement.

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?

Very concise (two words plus 'Free'), but lacks structured information. It is not front-loaded with the tool's core function.

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 zero parameters, no output schema, and no annotations, the description is grossly incomplete for a tool that presumably returns platform statistics. It fails to specify what data is returned or how it can be used.

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?

No parameters, so schema coverage is 100%. Description adds no meaning beyond schema, but baseline 3 is appropriate since no further param detail is needed.

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 'Platform statistics' is vague; no verb or resource specification. It fails to distinguish what statistics are provided, and sibling tools like list_tickers and query_range have more descriptive names.

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 guidance on when to use this tool versus siblings. The description provides no context for selection among related 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?

No annotations are provided, so the description must disclose all behavioral traits. It mentions cost but does not indicate read-only behavior, rate limits, pagination, or other side effects, leaving significant gaps.

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 two sentences, front-loading the purpose and following with a cost note. Every sentence adds value with no fluff.

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 has one parameter and no output schema. The description covers purpose and cost but omits return structure, pagination, or size limits, which is adequate for a simple list tool but not fully complete.

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 parameter, which already documents the YYYY-MM-DD format. The description adds no additional meaning beyond the schema.

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

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

The description clearly states the tool lists all tickers that traded on a given date, with a specific verb 'list' and resource 'all tickers'. It distinguishes from sibling tools like get_pricing or get_stats by focusing on ticker listing.

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

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

The description implies usage context (listing tickers for a date) and includes cost information, but lacks explicit guidance on when to use this tool versus alternatives or any 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?

No annotations are provided, so the description must carry the full behavioral disclosure. It mentions pricing ($0.02/ticker, no limit), which is useful, but does not disclose whether the operation is read-only, rate limits, error handling, or response format. The pricing info adds some transparency, but gaps remain.

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 extremely concise: 5 words plus pricing info. Every word is informative, and the main function is front-loaded. No unnecessary content.

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 tool has 13 sibling tools and no annotations or output schema, the description is too minimal. It lacks information on when to choose this tool over others, expected output, error scenarios, and any constraints beyond pricing. An agent would need additional context to select 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 baseline is 3. The description does not add any parameter-specific details beyond what is already in the schema (e.g., date format, tickers as list). It only repeats 'multiple tickers', which is already inferred from the schema description.

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 tool's function: querying multiple tickers for a single date. The name 'query_batch' combined with 'Multiple tickers for one date' distinguishes it from siblings like query_daily (single ticker) and query_range (date range).

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

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

The description implies usage (when needing data for multiple tickers on one date) but does not explicitly state when to use this tool versus alternatives like query_daily or query_range. No exclusions or alternative suggestions are provided.

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 provided, so description must disclose behaviors. It only states the output type but does not mention read-only status, rate limits, authentication, or any side effects.

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 very short (one sentence plus pricing), but the pricing note is distracting and not structurally helpful for tool invocation. It is concise but lacks useful structure.

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, so description should explain return format. It mentions 'OHLCV bars' but doesn't define the structure (e.g., open, high, low, close, volume) or date range behavior (inclusive/exclusive). Adequate for a simple tool but could be more complete.

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 clear descriptions for all three parameters. The description adds no extra semantic value beyond the schema, so baseline score of 3 is appropriate.

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

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

The description clearly states it returns daily OHLCV bars for a single ticker over a date range, using specific verbs ('bars') and resource ('daily' for one ticker), which distinguishes it from siblings like query_minute_bars and query_batch.

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 guidance on when to use this tool vs alternatives (e.g., query_minute_bars, query_range). The pricing note is irrelevant for selection. No exclusions or prerequisites mentioned.

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. It reveals the output type (OHLCV), scope (full trading day), interval constraints, and cost ($0.025). It does not mention timezone, extended hours, or data source, but provides key behavioral context.

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 sentence that front-loads the most important information: purpose, scope, interval range, default, and cost. No extraneous words; every element 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?

Given no output schema, the description adequately summarizes the return format (OHLCV bars) and scope. It lacks specifics on data structure, pagination, or error handling, but for a straightforward data query tool, it covers essentials. Could be improved by noting timezone or date range limitations.

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% (all properties have descriptions). The tool description adds only the default interval and range, which is already implied by the schema's allowed values. No additional parameter meaning beyond the schema.

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

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

The description clearly states it returns intraday OHLCV bars for one US stock over a full trading day, with a specific interval range and default of 3 minutes. This distinguishes it from sibling tools like query_daily (daily data) and get_bars (which might be more generic).

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 does not explicitly guide when to use this tool over alternatives like query_daily or get_bars. It implies intraday use for a single stock but lacks comparison or exclusion criteria. Sibling names hint at alternatives but no guidance is given.

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?

Discloses interval range, cost, and no day limit, which adds beyond schema. However, without annotations, it omits read-only nature, rate limits, and return format.

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?

Single sentence with parenthetical, 18 words, no redundancy. Efficiently conveys key information.

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?

Lacks output format description and comparison to similar siblings like query_minute_bars. Given no output schema, more explanation of return values would be beneficial.

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%, but description adds cost and day limit context beyond parameter definitions, enhancing agent understanding.

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?

Clearly states it retrieves multi-day intraday bars for one ticker, with interval range and default. Distinguishes from siblings like get_bars and query_minute_bars by specifying multi-day scope.

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?

Implies usage for intraday multi-day data with cost and no day limit, but does not explicitly compare to alternatives or specify when not to use.

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 provided, so description carries full burden. Only mentions cost, omitting other behaviors like read-only nature, rate limits, or error handling.

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?

Single sentence front-loads action and scope, includes cost without waste. Highly concise.

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 8 parameters and no output schema or annotations, description is brief. Lacks explanation of return format, performance, or error cases, but cost mention adds some context.

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 inputs are well-documented. Description adds no extra meaning beyond listing criteria categories; baseline score 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?

Description clearly states tool scans all US stocks with custom criteria (gaps, volume, change), distinguishing it from sibling tools that retrieve data for specific tickers.

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?

Description does not explicitly state when to use this tool vs. siblings; cost hint ($0.10 USDC) is a usage consideration but lacks guidance on alternatives.

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