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

With no annotations provided, the description carries the behavioral disclosure burden. It usefully discloses that values are null when history is too short, e.g. for recent IPOs, and sets expectations around the day-end candle data scope. This adds meaningful behavior beyond the bare schema.

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 with no filler. The primary purpose and time scope are front-loaded, and the edge-case note about null values is concise and valuable.

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 that an output schema exists, the description does not need to explain return values. It covers the essential context: symbol, lookback period, candle frequency, and a relevant edge case. It is slightly incomplete in not offering any alternative routing guidance, but it is otherwise sufficient for a compute 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 compensate for missing parameter documentation, but it does not. It only references 'a symbol' and 'technical indicators' without explaining the boolean toggles, their defaults, or how parameters affect computation. The parameter names are self-explanatory to some degree, but the low coverage is not compensated.

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 a specific action ('Compute'), a specific resource ('technical indicators for a symbol'), and a precise scope ('over the last year of day-end candles'). It is easily distinguishable from data-retrieval siblings like get_price_history or get_quote, though it does not explicitly contrast with technical_summary.

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 implied usage is clear: call this when you need computed technical indicators for a symbol. However, it provides no explicit guidance on when to prefer this over technical_summary or when not to use it, and it names no 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes the data content and an internal source, displayCompany, but reveals nothing about side effects, permissions, data freshness, or failure behavior. It does not contradict anything, but it adds little beyond the output content.

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 one compact sentence with a colon-led list of profile attributes. It is front-loaded with the core concept and contains no filler or repetitive phrasing.

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 read tool with an output schema, the basic invocation context is understandable. However, with no annotations and no usage guidance, the description is somewhat under-specified and relies on the agent to infer conventions and sibling differentiation.

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 schema has one required symbol parameter with 0% description coverage. The description does not explain the symbol format, case sensitivity, or how it maps to displayCompany, so it adds no parameter meaning beyond the schema's 'symbol' string. The single self-evident parameter prevents a score of 1.

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 identifies the resource as a company profile and enumerates its contents: capital structure, listing year, market lot, 52-week range, dividend status, and EPS. This is more specific than the title and helps distinguish it from quote/price tools. It lacks an explicit verb, but the tool name provides the action.

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 listed fields imply when the tool is appropriate, such as when an agent needs listing year, market lot, or dividend status data. However, the description does not explicitly state when to prefer this tool over siblings like get_quote or get_fundamentals, nor does it provide 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does reveal the specific output metrics and notes nuanced P/E categories, but it does not state whether this is a read-only operation, what happens on invalid symbols, data freshness, or any other behavioral caveats. The metric detail adds some transparency, but not enough for a fully 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?

The description is a single, tightly written sentence that front-loads the value proposition ('Analysis-ready fundamentals') and then itemizes the specific data points. There is no redundancy or 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 with one required parameter and an output schema exists, so the description does not need to explain return structures. The metric list gives enough context for basic invocation. Missing usage differentiation and behavioral caveats are covered by other dimensions, so this remains adequate.

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 schema has 0% description coverage and the description does not mention the sole 'symbol' parameter at all. While 'symbol' is conventional, the description adds no meaning about expected format, normalization, or valid values, which the low coverage requires.

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 identifies the resource as 'analysis-ready fundamentals' and enumerates the exact metrics included (EPS, P/E variants, dividend, reserves, market cap, 52-week range). It is distinguishable from sibling tools like get_quote or get_pe_ratios, though it does not explicitly call out those distinctions.

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 metric list: an agent can infer this is the tool to call when needing fundamental data points. However, there is no explicit guidance on when to prefer this over overlapping siblings such as get_pe_ratios or get_company_profile, and no exclusionary context is 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses a key limitation: the data is only retained for ~365 days due to DSE's rolling archive, which is critical for an agent to know before requesting longer ranges. It does not explain the return format, but an output schema exists to cover that.

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 no unnecessary words. The core action and resource are front-loaded, followed by the essential constraint in a parenthetical. Every word contributes 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?

For a simple one-parameter read tool with an output schema, the description is nearly complete. It covers the purpose, the rolling-year limitation, and the specific indices. The only minor gap is not clarifying what 'totals' refers to, but this is not critical for invoking 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?

The input schema provides no description for the 'days' parameter (0% coverage). The description compensates by explaining 'last N days' and the 365-day maximum, directly mapping to the parameter's meaning. It doesn't explicitly name the parameter, but the semantics are clear and inferable.

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 a specific verb and resource: 'Daily index history' for DSEX, DS30, and totals. It also specifies the time range (last N days), making it easy to distinguish from sibling tools like get_price_history which would apply to individual securities. The scope is concrete and unambiguous.

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 establishes a clear context: retrieving historical index data over a rolling period. It does not explicitly name alternatives or exclusions, but the mention of 'DSEX, DS30, totals' makes the intended use obvious for index-level analysis. This is clear context without explicit 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?

With no annotations, the description carries the burden and does disclose a meaningful behavioral trait: empty order-book sides outside trading hours are normal, so agents should not treat them as errors. It does not mention read-only status, rate limits, or data recency beyond the word 'live', but the note is useful.

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 with no filler: the first states the core payload and the second adds a necessary edge-case caveat. It is front-loaded 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 one-parameter tool with an output schema, the description covers the main purpose and an important non-obvious behavior. It is slightly incomplete around symbol format and when to choose this tool over nearby siblings, but otherwise adequate.

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 schema has one required parameter, symbol, with no description; the description also does not explain symbol format or meaning. Because schema coverage is 0%, the description should compensate, but it does not, leaving the agent to infer that symbol is a market ticker.

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 identifies the tool as a live order book with best bid/ask levels, volumes, and session price statistics, which clearly states what it does. It differentiates from quote and history tools by emphasizing order book depth, though it lacks an explicit verb and direct sibling comparison.

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 is provided on when to prefer get_market_depth over siblings like get_quote or top_movers. The only contextual note, that empty sides are normal outside trading hours, explains an expected condition rather than usage criteria.

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 discloses that results are returned newest-first and include titles, bodies, and post dates, and explains the symbol-omitted behavior as market-wide. It does not mention authorization or rate limits, but the read-only nature is strongly implied.

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: it states the core scope first, then the key parameter behavior and result format. Every clause adds useful information and there is 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 simple read-only news tool with an output schema and three optional parameters, the description is nearly complete. The main invocation behavior and return ordering are covered, though explicit explanation of days and limit would make it fully self-contained.

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. It explains the semantics of symbol, including the null market-wide case, but says nothing about the days or limit parameters, leaving their meaning to inference from names and 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?

The description clearly identifies the resource as company or market-wide news/disclosures and states the output ordering and fields. It does not explicitly name or distinguish sibling tools, but the news domain is unique among the listed siblings.

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 provides clear context: use this tool for company-specific or market-wide news, and omit symbol to get market-wide results. It does not offer explicit when-not-to-use guidance or alternatives, but there is no obvious competing news 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the output is a P/E table and lists ratio types, but it does not clarify data coverage, update frequency, point-in-time behavior, limitations, or whether the table is restricted to a particular market or index. This is insufficient for a no-annotation 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 a single efficient sentence with no filler, and the core scope 'P/E table for all instruments' is front-loaded. The trailing parenthetical is somewhat cryptic but compact. It could be clearer, but it 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?

This is a zero-parameter tool with an output schema, so the agent has structural information about the return value. However, the description does not explain what 'all instruments' covers or what the listed P/E variants mean in practice. Given no annotations and no usage guidance, it is minimally adequate but leaves 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?

The input schema has zero parameters and schema description coverage is 100%, so there is no parameter burden on the description. The baseline for zero-parameter tools is 4, and the description does not introduce any conflicting or misleading parameter information.

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 identifies the tool as returning a P/E table and scopes it to 'all instruments,' which distinguishes it from single-instrument siblings like get_quote or get_company_profile. It also lists ratio variants (interim basic/diluted, audited, trailing), adding useful specificity. It is slightly noun-phrase-like rather than verb-led, but the intent is unambiguous.

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 is given about when to use this tool versus alternatives such as get_fundamentals or get_quote. The phrase 'for all instruments' implies a market-wide use case, but there is no stated exclusion or comparison to sibling tools. The agent must infer when this is the right choice.

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 provided, the description carries the behavioral disclosure burden. It adds real value by stating that data is day-end rather than intraday, ordered oldest-first, defaulting to 90 days, and limited to a rolling one-year archive. This is meaningful context beyond the raw schema.

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 lead with the most important facts and then give parameter guidance. Every phrase earns its place, and there is no redundant restating of the tool name or schema.

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 that an output schema exists, the description does not need to detail return values. It covers core data type, ordering, date range options, defaults, and archive limits. It is slightly incomplete on sibling routing and edge-case parameter interactions, but overall it provides enough for correct invocation.

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. It explains that start/end are ISO dates and that days is an alternative with a default of 90 and a one-year ceiling. It does not explain ISO format details, the relationship when both start/end and days are supplied, or the symbol parameter, leaving some gaps.

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 identifies the tool as returning price history and specifies the data shape: 'Day-end OHLCV candles, oldest-first.' This is specific enough to separate it from quote, summary, or news tools, though it does not explicitly contrast with the closely related sibling get_index_history.

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 useful call-level guidance: provide ISO start/end, or use days with a 90-day default and a one-year archive limit. However, it does not explicitly state when to choose this tool over alternatives such as get_quote for current prices or compute_indicators for derived analysis.

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 burden of behavioral disclosure. It discloses the untraded-instrument behavior with 'Untraded instruments carry traded=false', which is valuable. It does not discuss error cases or data latency, but these are less critical for a simple read-only quote 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 sentences with no filler. The key purpose is front-loaded and the behavioral note is a compact second 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?

For a one-parameter tool with an output schema, the description covers the essential purpose, the scope (single instrument), and a non-obvious output behavior. Nothing important is missing for an agent to select and call 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 0%, so the description should compensate for the single `symbol` parameter. It clarifies that the tool targets one instrument but does not explain accepted symbol formats, casing, or how to find the correct symbol via search_symbols.

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 states a specific action and resource: retrieving the latest quote for one instrument, and enumerates the returned fields (LTP, day range, close, YCP, change, trades, value, volume). This clearly separates it from broader market tools like market_summary or historical tools like get_price_history.

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 'Latest quote for one instrument' gives a clear condition for use: when you need a current snapshot for a single symbol. It does not explicitly list alternatives or when-not-to-use conditions, 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.

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

With no annotations, the description carries the full burden and does disclose the key output concepts: live/closed status, session hours, and local time. It does not mention data source freshness, potential delays, or whether the status is exchange-provided, but for a simple status tool this is reasonable.

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, tightly written sentence that front-loads the core purpose and lists the exact output elements. Every word adds value and there is no 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?

Given there are no parameters and an output schema exists, the description is complete for an agent to select and invoke the tool. It captures the essential semantic content without requiring additional explanation.

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 has zero parameters, so there are no parameter semantics to document. The description adds no parameter information, but none is needed; the no-input schema is already self-evident.

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 specifies the resource (DSE market) and the exact information returned: live/closed state, session hours, and Dhaka local time. While it lacks a verb, it clearly defines scope and distinguishes itself from broader siblings like market_summary.

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 use when an agent needs the current market state or trading session hours. However, it does not explicitly contrast with related tools such as market_summary or get_quote, nor does it state when not to use this tool.

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 disclosure burden. It does communicate that the result is a 'latest' snapshot sourced from a '30-day market information table,' implying a read-only, current view. However, it does not explicitly state that it has no side effects, whether data is cached, or how often it refreshes.

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, focused sentence with no wasted words. It front-loads the core concept ('Latest market snapshot') and then lists the specific data elements, making it easy for an agent to parse quickly.

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-parameter tool with an output schema present, the description is nearly complete: it names all returned content areas and the data source. The only notable gap is the absence of routing context versus similar market tools, but this does not prevent correct invocation.

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 has zero parameters, so the schema fully defines invocation requirements and the description need not explain parameter details. The baseline of 4 applies because there is nothing meaningful to add about 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?

The description clearly identifies the resource as a latest market snapshot and enumerates its contents: DSEX/DS30 indices, changes, session totals, and DSES. It is not phrased with a strong action verb, but the noun-phrase 'Latest market snapshot' makes the retrieval behavior clear enough and helps distinguish it from historical or sector-specific siblings.

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 no explicit guidance about when to choose this tool over alternatives such as market_status or get_index_history. The reader can infer that it is for a current market overview, but there are no stated exclusions, conditions, or sibling routing hints.

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 present, the description carries the full behavioral burden. It discloses several non-obvious behaviors: case-insensitive sector matching, P/E fallback logic, exclusion of untraded instruments, and sorting by turnover. This goes well beyond a simple 'filter stocks' 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?

Two tightly written sentences convey the tool's purpose, filtering criteria, behavioral nuances, exclusions, and sort order without any wasted words. Key information is front-loaded 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?

The description covers all major behavioral aspects needed to call the tool correctly, especially given that an output schema exists. The only notable gap is the 'limit' parameter, which is not described at all; otherwise, the description is sufficient for a read-only screening 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 compensate. It adds meaningful semantics: sector is a case-insensitive substring, pe_max uses interim basic P/E falling back to trailing, and price range/volume are explained. However, the 'limit' parameter is not mentioned in the description, leaving that parameter's semantics solely to 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 opens with a specific verb and resource, 'Filter the live board', and enumerates the exact filtering dimensions. This clearly distinguishes the tool from sibling tools like top_movers or market_summary, which serve different purposes.

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 when to use the tool—when you need to screen live stocks by sector, valuation, price, or volume—but it does not explicitly mention alternatives or conditions that would route an agent to a sibling tool. There are no exclusions or when-not-to-use statements.

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 of behavioral disclosure. It usefully reveals case-insensitive matching, but it does not state whether matching is exact, prefix, partial, or fuzzy, how results are ordered, or how the limit parameter behaves. For a search tool, this is a meaningful 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 sentence with no filler. The core action, target resource, searchable fields, and case-insensitive behavior are all front-loaded in a compact and readable way.

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 two-parameter search tool with an output schema, this is close to adequate. However, with no annotations and a terse description, it leaves unresolved the matching behavior, limit semantics, and routing versus sibling tools. The output schema does cover return shape, which prevents a lower score.

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. It adds real meaning to query by specifying that it accepts a trading code or company name and is case-insensitive, but it says nothing about limit beyond the schema's type and default. One of two parameters remains semantically underdescribed.

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 ('DSE instruments'), and precise search dimensions ('trading code or company name'). The case-insensitive note adds useful precision and distinguishes this from sibling tools like screen_stocks, which filter by broader criteria rather than instrument identifiers.

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 the tool is for looking up instruments when you already have a trading code or company name, but it gives no explicit when-to-use conditions, exclusions, or alternatives. It does not explain how this differs from screen_stocks or other sibling tools that might also locate instruments.

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 provided, the description carries the full burden of behavioral disclosure. It transparently reveals that this is an aggregation over live quotes, what metrics are computed, and that results are sorted best-to-worst. It does not discuss failure modes or data-source caveats, but for a zero-parameter read-only aggregation this is sufficient behavioral transparency.

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 with no filler; the action, target, computed fields, and ordering are all front-loaded. Every segment of the sentence adds useful information, and there is no redundancy with schema or annotations.

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 tool with an output schema present, the description is nearly complete: it states what data is aggregated, what fields are returned, and how the result is sorted. The only minor gap is the absence of explicit guidance about when to select this tool instead of a sibling like market_summary, but this does not prevent correct invocation.

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 schema has zero parameters, so the baseline for this dimension is 4. The description has no parameter explanations, but none are needed because the input schema is empty and additionalProperties is false. The tool is fully invocable with no ambiguity.

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 operation ('Aggregate live-quote performance per sector') and specifies the exact outputs: advancing/declining counts, average change percent, and ordering from best to worst. This clearly distinguishes it from market-summary or top-movers siblings, which operate at market or symbol level rather than sector level.

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 when to use the tool through 'per sector,' but it never explicitly states when to prefer this over alternatives like market_summary or top_movers, nor does it name any exclusions. The usage context is inferable, not 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?

With no annotations provided, the description carries the behavioral disclosure burden. It openly states the tool is rule-based and informational only, and it lists the exact outputs the agent can expect. It could add caveats about data requirements or limitations, but what is provided is useful and clear.

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 dense sentence with output components listed in a scannable, comma/semicolon-separated structure. It is front-loaded with the core purpose and contains no filler or repetition.

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 one obvious parameter and an output schema, the description covers both input purpose and output contents well. It omits minor details like required price-history depth for SMA50/200 and exact symbol conventions, but these are not critical for normal use.

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 `symbol` parameter. It doesn't explicitly describe the symbol format or accepted values, but the surrounding description makes clear that the symbol is the security being analyzed, adding some meaning beyond 'string.'

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 defines a 'rule-based technical read' and enumerates the concrete components: SMA50/200 cross, RSI zone, MACD direction, Bollinger position, support/resistance, volume context, and a plain-language outlook. This distinguishes it from raw-data sibling tools like compute_indicators or get_quote.

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 describing the tool as a technical summary and 'informational only,' but no explicit when-to-use or when-not-to-use guidance is given. It does not name alternatives such as compute_indicators or get_price_history, so the agent must infer selection from the purpose.

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 behavioral burden. It discloses the circuit-breaker rule for gainers/losers and the live-quote/turnover logic with untraded instruments excluded, which are non-obvious data behaviors. It does not detail ordering or output size, but an output schema exists and these are minor 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?

Two compact sentences front-load the parameter value list and add only essential behavioral detail. No filler or repeated schema 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?

For a single optional parameter with an output schema, the description provides everything needed to call the tool: possible values and special calculation rules. The default value is already in the input schema, so no duplication is needed.

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 must define the category parameter. It enumerates all four valid values and explains the conceptual difference between the gain/loss lists and turnover leaders. This fully compensates for the empty 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 says the tool returns top movers and enumerates the four category values, making the resource and scope identifiable. It lacks an explicit action verb and does not name sibling tools, but the category list strongly distinguishes it from tools like market_summary and sector_performance.

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 category values and their meanings make it clear that this tool is appropriate when an agent needs top movers by one of the listed metrics. It does not explicitly say when to choose this over siblings like market_summary or get_quote, nor does it mention exclusions.

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