closelook-intelligence

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond them: the data is end-of-day, it covers the entire headline index family, and it details the returned fields, which matters because there is no output 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 sentences, zero filler: the first front-loads scope and returned metrics, the second supplies the value proposition. Every clause 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?

For a parameterless read tool with annotations covering safety and no output schema, the description supplies enough: what indices, which metrics, and EOD cadence. Minor gaps remain around freshness/lag and timezone of "end-of-day," but nothing an agent needs to invoke it correctly is absent.

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 takes no parameters, so the schema carries nothing to document and the baseline is 4. Nothing in the description misleads about inputs.

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 operation (side-by-side comparison) over a named resource (all Closelooknet headline indices) and enumerates both the index set and the metrics (last close, 1d, 1w, MTD). That scope implicitly separates it from single-index siblings like get_index_snapshot, but no sibling is named explicitly, so it stops short of a 5.

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

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

"The fastest read on where the AI trade rotated, end-of-day" implies when this tool is the right choice (a quick EOD macro rotation scan) and hints that deeper tools exist for other questions. It names no alternative and gives no when-not condition, so usage is only implied.

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=true, destructiveHint=false and openWorldHint=false, so the agent knows this is a safe, closed-corpus read. The description usefully adds the corpus size and vocabulary categories, but says nothing about behavior on unknown/out-of-glossary terms or what a definition response looks like.

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 dense sentence with the action verb front-loaded and the scope detail appended; no filler or repetition of the title.

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-only lookup with no output schema, the description gives enough to call it correctly; only the miss/not-found behavior is unaddressed, which is a minor gap.

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

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

Schema description coverage is 100% and the schema already supplies example values ('Korea discount', 'MACD'), so the description carries little extra parameter meaning beyond establishing that lookup is against the glossary. Baseline 3 is appropriate for a fully-documented single free-text 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?

States a specific verb+resource ('Get Closelooknet's definition of a financial or market term') and scopes it to a 260+ entry glossary with named coverage areas, so an agent can immediately tell it apart from the market-data siblings (get_index_snapshot, get_tape, etc.). Nothing about the intent is ambiguous.

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?

There is no explicit when-to-use guidance and no exclusions. It is not stated whether this is the right tool when the term might also appear in search_closelook or get_latest_view content, so the routing decision is left entirely to inference.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety and data-source scope are covered. The description adds useful context beyond them: the Friday publication cadence, that it mirrors a public web page, and what the content consists of. It still says nothing about return format or how many picks exist.

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?

It is a single front-loaded sentence, which is structurally sound, but it is dense with opaque editorial jargon and a redundant brand prefix that duplicates the title. The one genuinely operational fact ('Weekly (Friday)') is buried at the very end.

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

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

For a two-parameter read-only retrieval tool with no output schema and annotations covering the safety profile, the description supplies enough to know what is being fetched and how often it changes. Return shape is only loosely implied, which is the main residual gap.

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

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

Schema description coverage is 100%, with both 'all' and 'date' fully documented in the schema, so baseline is 3. The description never references either parameter and adds no format or default-behavior detail beyond what the schema provides.

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

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

The description names a concrete resource — a weekly editorial pick from the Directional Flow engine, with its content components (setup bullets, house reading, closing forecasts). An agent can tell this returns curated weekly content rather than a market-data utility like get_df_ranking, though the branding-heavy phrasing ('Closelooknet's', 'house reading', 'STANDING') blurs the exact 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?

No guidance on when to use this versus the many get_* siblings, and no prerequisites or exclusions are stated. The only usable cue is the cadence note 'Weekly (Friday)', which implies but does not state that older picks require the date/all parameters.

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=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one trait beyond that — 'End-of-day' cadence — which tells the agent the freshness of the data. It adds nothing about auth, rate limits, or whether values are cached/revisable.

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?

It is a single front-loaded sentence that leads with the product name and then enumerates the payload, ending with the cadence ('End-of-day'). It is dense but every clause adds a distinct data category; only the sourcing brand name ('Closelooknet's') is arguably filler.

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

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

With no output schema and no parameters, the description carries the burden of describing return content, and it does so concretely (ladder rungs, IG/BBB/B/HY spreads with deltas/percentiles, tier aggregates, per-issuer flags). What it lacks is any statement of return shape/format or granularity, leaving minor ambiguity for an agent deciding whether to call it.

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 takes no parameters, so there is no parameter semantics to clarify; the baseline for zero-param tools is 4. Nothing in the description misleadingly implies inputs.

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

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

Names a specific resource (AI credit stress data on the AI buildout funding ladder) and enumerates its content — funding-ladder tiers, FRED credit spreads, tier aggregates, per-issuer flags — which distinguishes it from generic market siblings like get_macro_regime or get_tape. However it never states an explicit verb ('returns'/'retrieves'), and no sibling is named to sharpen the boundary, so it stops short of a 5.

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

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

The description says what the payload contains but gives no when-to-use guidance, no conditions, and no alternatives. An agent must infer from context that this is the credit-stress lens versus get_sovereign_pressure or get_macro_regime. No exclusions or trigger conditions are present.

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=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description usefully adds a hard coverage boundary ('Last 90 trading days') and clarifies that it mirrors the closelook.net/days/<date>/ page, but says nothing about response shape or pagination behavior.

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

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

A single front-loaded sentence whose clauses each carry information: the source, the date/latest behavior, the enumerated payload, and the coverage limit. Slightly dense with the URL reference and em-dash appositive, but nothing is wasted.

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

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

With no output schema, the description carries the burden of describing returns and does so by naming the three content types and their links. The remaining gap is the response envelope (single object vs. list when 'days' is supplied), which is not stated.

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

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

Schema description coverage is 100% and both parameters are already documented in the schema (date format and 'omit for the latest', plus the 1–14 day range). The description reinforces the date-omission behavior and the 90-day window but adds no syntax or default detail 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 names a specific resource (the trading-day hub) and enumerates exactly what it returns — Morning 10, Midday 10, and Daily Pulse editions with links — which is far more concrete than a generic 'get day data'. It does not explicitly contrast itself with siblings like get_latest_view or get_wire, but the enumerated payload makes it distinguishable.

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?

It implies usage by noting it accepts a date 'or the latest' and is scoped to the last 90 trading days, which tells the agent when the tool is applicable. It offers no explicit when-not guidance and names no alternative tool for overlapping needs (e.g. latest-view or news 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?

Annotations already cover read-only, non-destructive, and closed-world status. The description adds real behavioral context beyond them: nightly/EOD refresh cadence, the ~330-stock coverage universe, and the scoring method (recency-weighted regression on log-closes). It does not state caching or latency, but the added timing and methodology are substantive.

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

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

Front-loaded with what the ranking is and how it is computed, then the seven cuts, then the mirror URL and cadence. Dense but every clause carries information; the only near-redundancy is the URL, which does help identify the canonical source.

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 and no required parameters, the description must carry the 'what comes back' burden; it names the seven ranking views and the scored universe, which is adequate for selection. It stops short of describing the row shape or ordering guarantee, a minor gap for a 2-parameter read tool.

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

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

Schema coverage is 100%, so the baseline is 3, but the prose maps enum values to meaning the schema labels alone do not convey — e.g. 'rising fastest (21d)', 'this week's biggest moves (5d)', 'steadiest builders (63d)' — clarifying the lookback window behind momentum/short-term/quarter. The limit parameter adds nothing beyond the schema's own 1-25/default-10 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?

States a specific subject and scope: the nightly Directional Flow trend-quality score, its methodology (recency-weighted regression on log-closes), ~330 covered stocks, and seven ranking cuts. An agent immediately knows what this returns. It does not distinguish itself from the sibling get_ranking, though the named endpoint (closelook.net/stocks/rankings/directional-flow) implicitly does.

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?

Enumerating the seven cuts (top scores, rising fastest, biggest moves, steadiest builders, still getting stronger, getting weaker, falling fastest) implicitly tells the agent which view to pick, but there is no explicit when-to-use / when-not guidance and no routing versus get_ranking or get_signal_scores.

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=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the composition of the read (which sub-metrics it returns) and the 'End-of-day' update cadence, which tells the agent the data is not intraday.

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 dense clause enumerating the read's components, followed by a positioning line and a cadence tag. It is front-loaded and every sentence carries information, though the opening branding phrase ('Closelooknet's factor-regime read') is slightly redundant with the title.

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 and no parameters, the description carries the burden of conveying what comes back, and it does so by naming the ratio, trend, percentile, and rate-of-change dimensions. The 'End-of-day' note covers freshness. It is complete enough to call the tool confidently, with only minor ambiguity about the exact response shape.

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 takes zero parameters, so there is nothing for the description to disambiguate. Baseline is 4 for a no-parameter tool; the description correctly signals that this is a fixed, argument-free read.

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

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

States a specific verb and resource (factor-regime read) and names the exact instruments (SPMO vs SPLV), the comparison basis (50-day trend), and the derived metrics (3-year percentile, 20/60-day ROC). This distinguishes it clearly from siblings like get_macro_regime and get_ratio_pair, which cover different regime concepts.

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 line 'the fastest single read on risk appetite under the index surface' gives an implied usage context, but there is no explicit when-to-use/when-not-to-use guidance and no named alternative (e.g., get_macro_regime for broader regime, get_ratio_pair for arbitrary pairs). The agent must infer the routing decision.

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 cover the safety profile (readOnly, non-destructive, closed-world), so the description's incremental value is the data cadence ('end-of-day') and the payload contents (level, recent returns, strongest/weakest sub-indices). That meaningfully helps an agent know what it will get and how fresh the data is.

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 the resource, the enumeration, the freshness qualifier and the return contents — no filler, and the core purpose 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?

For a one-required-param lookup with no output schema, the description supplies both the return shape and the end-of-day cadence, so nothing an agent needs to call or interpret the tool is missing.

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

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

Schema coverage is 100%, so baseline is 3, but the description goes further by defining each enum value (RUBIN = AI buildout, HALO = non-AI growth, AW40 = AI deployment, AEI = agentic stack, EUROAI), which the schema only labels generically as 'Index code'.

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

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

States a specific verb+resource ('Current snapshot of one proprietary Closelooknet index') and enumerates the five index codes with short glosses. The word 'one' implicitly separates it from the multi-index sibling compare_indices.

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 'one ... index' — an agent can infer this is the single-index lookup and compare_indices is the multi-index one — but there is no explicit when-to-use or when-not statement and no alternative is named.

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=true, openWorldHint=false, and destructiveHint=false, so safety is covered. The description adds useful return-content detail: headline, core statement, and link for each piece, which is valuable given the absence of an output 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 a single, well-structured sentence that front-loads the resource and then specifies the returned content. Every clause earns its place 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 zero-parameter read-only tool with no output schema, the description fully covers what the agent needs: it names the resource, its recency, and the exact components and fields returned. Nothing essential 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 tool takes zero parameters, so there is no parameter semantics burden. With no inputs to document, the baseline score of 4 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?

States a specific resource (Closelooknet’s latest published market view) and enumerates its two components: today’s Morning 10 and the latest Daily Pulse thesis. The content names (Morning 10, Daily Pulse) distinguish it from generic siblings like get_wire or get_tape without requiring schema inspection.

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 retrieving the latest published view, but it offers no explicit when-to-use guidance, no exclusions, and no alternatives among the many sibling tools. Usage is inferable but not clarified.

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 cover the safety profile (readOnlyHint=true, openWorldHint=false, destructiveHint=false), so the bar is lower, and the description adds real value on top: data provenance (~26 and ~19 FRED series), update cadence ('Daily on FRED release days'), and the granularity of returned data (bucket-level z-scores). It omits return shape details and any latency/rate notes, keeping it from a 5.

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

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

The content is front-loaded — it names both monitors first, then details their outputs — and packs high information density into a few sentences without filler. It is somewhat list-heavy with series and bucket counts, but every clause carries signal for an agent deciding whether to call it.

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 carries the return-value burden and largely meets it by enumerating the fields each monitor emits. Combined with annotations covering safety and a fully documented single parameter, an agent has enough to call this correctly; explicit usage routing is the only notable gap.

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

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

Schema description coverage is 100% — the single 'monitor' parameter has an enum with a documented default ('Which monitor (default both)'). Per the rubric this earns the baseline 3; the description adds no extra syntax or format semantics beyond what the schema already provides.

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

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

The description states a specific resource (two macro monitors) and enumerates exactly what each returns — score, regime, direction, structural-vs-transitory, supply shock, recession risk — plus the underlying FRED series counts and bucket counts. It is immediately clear what the tool produces. It does not, however, differentiate itself from confusable siblings such as get_factor_regime or get_money_temperature, so it falls short of a 5.

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

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

There is no guidance on when to call this tool versus alternatives, nor on how to choose among the 'both'/'inflation'/'growth' monitors beyond restating the enum default. The only timing hint ('Daily on FRED release days') concerns data freshness, not invocation context. An agent gets no routing help.

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=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description does add genuine behavioral context beyond that: it states the board refreshes daily at 22:30 UTC and mirrors a specific public page, which tells the agent how stale the data may be. It does not describe return format or size, so it stays at a 3.

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 dense sentence with the resource name front-loaded, followed by a short freshness note. Nothing is redundant, though the unglossed jargon ("ORCL torque", "MAGS trendline read") makes it denser than it needs to be for an unfamiliar reader.

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 and no parameters, the description carries the burden of saying what comes back, and it does so by enumerating the board's components. The only real gap is that it never explains the field semantics behind the branded terms.

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 takes zero parameters and the schema is empty, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly implies the board is fetched whole with no filtering arguments.

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 concrete resource (a daily hyperscaler-cohort board) and enumerates its contents: Mag names with 1d/1w/1m/1y changes, the benchmark set (QQQ, SPY, SOXX, XLK, IGV, MAGS), the MAGS trendline read, and the ORCL torque. That is far more specific than a tautology and lets an agent distinguish it from get_tech_board or get_tape. It loses a point only because the branded terms are not glossed.

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?

There is no statement of when to call this versus the many sibling boards, nor any exclusions or prerequisites. The only usable cue is the daily 22:30 UTC cadence, which tells the agent about freshness but not selection 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?

Annotations already declare this is a safe, non-destructive, non-open-world read. The description adds genuinely useful context beyond them: the data derivation (three years of daily closes), the exact metrics computed (1d/1m/3m/YTD/1y changes plus 52-week range), and the update cadence ('Daily after the US close'). It does not cover error behavior or result limits, but for a read tool with annotations this is solid.

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

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

Front-loaded with the resource and its scope, then a compact list of returned metrics, then the URL mirror and cadence. The opening sentence is dense with examples, but every element (scope, fields, source, freshness) earns its place; no filler sentences.

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 carries the return-value burden and does so by listing the level, multi-horizon changes and 52-week range. It also documents data provenance and staleness, which matters for a market data tool. Only the lack of sibling differentiation and result-size/error notes keeps it below 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% and the single parameter is fully documented there (vendor symbol or label fragment, with examples, and the omit-to-list behavior). The description restates the board context but adds no new syntax or matching rules beyond what the schema already provides, so the baseline of 3 applies.

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

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

The description names a specific resource (Closelooknet's market board instruments) and enumerates exactly what is covered (indices, FX, crypto, futures proxies, US funds) with concrete examples. It also states the fields returned. It stops short of distinguishing itself from lookalike siblings such as get_index_snapshot or get_price_history, so it is clear but not fully disambiguated.

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 rather than stated: the description explains that omitting the symbol lists the whole board and that data refreshes daily after the US close, which tells an agent how the tool behaves. However, there is no explicit when-to-use versus siblings like get_index_snapshot or compare_indices, and no 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?

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description only needs to add non-obvious context. It does: it discloses the payload composition (eight instruments, five scored dimensions, technical states, absorption ratio), the daily cadence, and that it mirrors a specific public page. It omits any latency, caching or freshness guarantees, but the added content detail is substantive.

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

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

A single front-loaded sentence names the source, the resource, the instruments and the metrics, then ends with the cadence. It is dense with useful specifics rather than padding. The score dash formatting and long enumeration make it slightly harder to scan, keeping it just short of 5.

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 carries the burden of describing the return value, and it does so well by enumerating instruments, score dimensions and the absorption ratio. Combined with annotations that establish it as a safe read, an agent has enough to call it correctly. Only the absence of routing guidance against sibling regime tools is a gap.

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

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

The tool takes zero parameters, so the baseline of 4 applies. There is nothing to mis-specify and the description correctly implies a parameterless, fetch-everything call.

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 resource (the house money-regime monitor) and enumerates exactly what it returns: eight named instruments scored 0-100 across five named dimensions plus an absorption ratio. That is far more specific than a tautology. It does not, however, explicitly contrast itself with close siblings such as get_macro_regime, get_credit_stress or get_factor_regime, so the agent must infer the boundary.

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

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

There is no when-to-use, when-not-to-use, or alternative-tool guidance. The only implicit cue is the word 'Daily,' which hints at a recurring cadence but says nothing about selecting this tool over the many other regime/snapshot siblings.

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=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful non-annotation behavior: weekly refresh cadence (Friday close), the free-tier data boundary (no cost basis or P&L), and the source it mirrors. It does not state a response format, which keeps it short of a 5.

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

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

Content is front-loaded: what the tool returns comes first, then the free/subscriber boundary, then cadence. It is dense but every clause except the 'mirrors closelook.net/portfolios/' line carries decision-relevant 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?

With no output schema, the description carries the burden of describing return values, and it does so by listing the fields returned (snapshot date, position count, top-10 holdings, headline return) and their scope (free vs subscriber). It stops short of field naming or pagination/size limits, leaving a small gap for a multi-book tool.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning by mapping human-readable book names (AI Build-Out, Hypergrowth, Global Tech 50, Rubin EW, T1, etc.) onto the slug values the schema enumerates. That mapping helps the agent choose the right slug, though it does not add format or default semantics beyond 'omit for all'.

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 resource (closelooknet's live reference portfolios) and enumerates exactly what the snapshot contains: date, position count, top-10 holdings by weight, headline return vs deposited capital. It also names the books covered, so an agent can distinguish it from siblings like get_index_snapshot or get_ranking without opening a schema.

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

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

The description implicitly scopes usage via 'exactly what the free page shows' and the subscriber-only caveat, which tells the agent this is a public-tier summary rather than full composition. However, it never states when to prefer this over sibling tools such as get_index_snapshot or get_stock_snapshot, and gives no explicit exclusions or 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false. The description adds useful context beyond annotations: EOD nature, coverage of ~2,500 tickers, and the exact price-history fields returned. It stops short of describing latency, pagination, or data freshness, but the read-only safety profile is already covered.

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 core purpose is front-loaded, followed immediately by the returned fields and ticker-format rules, all of which are directly relevant to invoking the tool.

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 exists, so the description carries the burden of explaining return values. It lists the key returned measures (latest close, changes, 52-week range, last ten sessions) and ticker conventions, making it sufficiently complete for a price-history read. Minor gaps remain around output format, currency handling, and timezone, but the essential calling information is present.

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 single ticker parameter is already documented. The description adds valuable formatting rules beyond the schema: US tickers are bare (NVDA) and foreign tickers require exchange suffixes (005930.KS, 6857.T, ASML.AS).

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

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

States a specific verb+resource: 'End-of-day price read' for tickers in Closelooknet's data lake. It enumerates the exact outputs (latest close, close-to-close changes over multiple horizons, 52-week range, last ten sessions), which clearly differentiates it from snapshot or ranking 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?

Usage is implied by 'End-of-day price read' and the listed outputs, but there is no explicit when-to-use vs alternatives guidance or exclusions. It does not name sibling tools or state when another tool would be more appropriate.

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 mark this as a safe, non-destructive, closed-world read, so the bar is lower. The description still adds real behavioral context: the record spans ~10 prints, includes beat-vs-reaction divergence, and degrades gracefully to a coverage/calendar listing when no ticker is supplied. It omits return format and any freshness/staleness caveats.

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 front-loaded sentences that deliver the content inventory before the usage instruction, with little redundancy. The line 'The gap between beat-rates and reactions is the product' is promotional framing rather than operational guidance and is the one sentence that does not fully earn 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?

With no output schema, the description correctly carries the burden of describing return contents and does so in detail. Only minor gaps remain, such as pagination or how coverage limits are communicated, which are unlikely to block 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 coverage is 100% and the single parameter already documents 'Omit to list coverage', so the baseline is 3. The description restates the omit behavior and adds that the no-ticker response includes the forward calendar, but contributes no syntax or format detail 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?

States a specific resource (Closelooknet's Print Record for a covered ticker) and enumerates exactly what it contains: ~10 earnings prints with EPS/revenue beat-or-miss, 3-day price reaction, headline counts, curated metric line, and next scheduled print. No sibling tool covers earnings prints, so an agent can distinguish it immediately.

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

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

Explicitly tells the agent to call without a ticker to see current coverage and the forward calendar, which covers the optional-parameter case well. It stops short of naming when to prefer a sibling tool or any prerequisites/limits on coverage.

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=true, openWorldHint=false, and destructiveHint=false, establishing the safe-read profile, so the description need not re-state safety. It adds useful provenance and scope (data windows of ~72 cuts/126 trading days, source mirror closelook.net/stocks/rankings/), but discloses no operational behavior such as freshness, caching, or rate limits. Modest added value over 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?

It is a dense, front-loaded paragraph: the tool's identity and relationship to get_df_ranking lead, followed by the family breakdown. Nearly every clause carries information (universe sizes, view options, data source). It is crowded but not padded; sentence structure is efficient given the breadth of families covered.

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?

There is no output schema, so the description carries the return-format burden, yet it never describes the shape of the result (columns, metrics per row) beyond the qualitative 'ranked' framing. Given three families with distinct metrics, an agent would benefit from knowing the return structure. Adequate for choosing the tool, incomplete for interpreting 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 coverage is 100%, so the baseline is 3, but the description goes further by explaining what each family actually measures and mapping which views (top/momentum, leaders/fragile/unstable, divided/today/broadest) belong to which family. This semantic detail helps an agent choose family/view combinations beyond the bare enum values.

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 the resource (Closelooknet ranking families) and enumerates each family with its underlying universe (US-listed ETFs, ~2,700 stocks, 40 funds) and dimensions, so an agent knows exactly what data is returned. It explicitly positions itself as the sibling of get_df_ranking (end-of-day), which aids discrimination. It stops short of a crisp verb-first sentence like 'returns ranked lists,' but the resource and scope are 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?

Labeling these as the 'other daily ranking families (siblings of get_df_ranking, end-of-day)' gives implicit routing context, and the per-family view names hint at when each cut applies. However, there is no explicit when-to-use/when-not or a stated condition distinguishing this tool from get_df_ranking or other ranking-style siblings. Usage is implied rather than spelled out.

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=true, so the safety profile is covered. The description adds real behavioral context beyond that: it is a fixed preset set (not arbitrary pairs), values are weekly since each pair's first common date, and the exact per-pair fields (current ratio, 1y change, all-time low/high with dates, percentile, distance from low). It omits pagination/rate-limit detail but adds substantive scope and cadence information.

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

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

Front-loads the domain and coverage up front, then lists the facts returned. It is dense but every clause carries information; the pair enumeration overlaps somewhat with the schema's slug list, which keeps it just short of a 5.

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 carries the burden of describing return content, and it does so thoroughly (per-pair fields, weekly resolution, historical scope). It does not describe the response envelope or error/empty behavior, but an agent has enough to call and interpret 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% and the schema already documents the slug-or-omit behavior, so the baseline is 3. The narrative pair list partially maps names to slugs but adds little beyond what the schema's enum-like description already provides.

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

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

States a specific verb+resource (relative-performance ratio facts for ten preset pairs) and enumerates exactly what is returned per pair. It is clearly distinguishable from siblings like compare_indices or get_index_snapshot because it is charted ratio data, not index levels.

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 through 'relative-performance facts for ten pairs' and the closelook.net/lab/ratio/ mirror, but never states when to choose this over compare_indices, get_price_history, or get_index_snapshot. It gives context but no explicit when/when-not or 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?

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds genuinely useful behavioral context beyond that: the data is ETF-vehicle derived, EM is approximated from country funds, and results refresh daily after each regional close — real provenance and freshness caveats.

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 core scope is front-loaded in the first clause and the paragraph is appropriately short for a read-only data tool. Some phrasing ('The decomposition institutions see', the branded opener) is denser prose than needed, but it stays within one tight block.

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 the work of describing return content — per-region and per-sector leaders/laggards across four windows — which is enough for an agent to know what comes back. It lacks any note on volume or shape of the payload, but that is a minor gap.

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

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

Schema description coverage is 100% and both parameters are enums with their own descriptions, so the schema carries the load. The description echoes the region and window values ('5d, 1m, 3m, ytd', 'US, Europe, Asia-Pac DM, EM') but adds no syntax or format meaning beyond the schema, making the baseline 3 correct.

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 resource (eleven GICS sectors × four regions returns) and states what is returned (returns over a window, with leaders and laggards per region and sector). An agent can grasp the tool's function immediately, but it never contrasts itself with siblings like get_ranking or compare_indices, so differentiation is left to inference.

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

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

Usage is only implied: the reference to 'closelook.net/lab/sectors/' and the daily-after-close cadence hint at the context, but there is no explicit when-to-use, when-not-to-use, or named alternative among the 24 siblings. An agent must infer it is the sector-rotation decomposition 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?

Annotations already establish the safe read-only profile (readOnlyHint=true, destructiveHint=false), so the description only needs to add context — and it does: it discloses coverage scope ('~300 covered names') and update cadence ('End-of-day'). Those are genuine behavioral traits an agent cannot get from the 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?

A single dense sentence that front-loads the resource and then lists contents; every clause carries payload. It is jargon-heavy but not padded, and it earns its length for an output-schema-less tool.

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 must describe the return, and it does so thoroughly by enumerating composite rank, all seven sub-scores, and three named ratios. The notable gap is behavior for tickers outside the ~300 covered names, but otherwise an agent has enough to 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?

With a single parameter at 100% schema coverage, the schema fully documents the ticker input, and the description adds no format or semantics beyond it. Baseline 3 is appropriate when the schema does all the parameter work.

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

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

The description names a specific resource (Closelooknet per-ticker signal scores) and enumerates its exact composition: composite rank, seven named sub-scores, and three literature ratios. This is far more than a restated title, though it does not explicitly contrast itself with siblings like get_stock_snapshot or get_df_ranking.

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?

There is no statement of when to use this tool versus alternatives, no prerequisites, and no exclusions. Usage is only weakly implied by 'per-ticker scoring,' leaving the agent to infer routing among 25 siblings on its own.

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=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description usefully adds that this is a daily snapshot mirroring a specific web page and defines the Pressure Index sign convention ('high = broad, long-end-led sovereign sell-off'), but says nothing about freshness guarantees beyond 'Daily' or the response shape.

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

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

Everything sits in one dense sentence that front-loads the board name before listing metrics; every clause specifies concrete return content rather than filler. It is a bit run-on, but no sentence is wasted.

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

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

With no output schema, the description carries the burden of conveying return content, and it lists the metric families (aggregated yields, slopes, per-country changes, Pressure Index) thoroughly enough for an agent to decide on and interpret the call. Missing only details like field labels or the geographic breakdown order, which are minor.

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 takes zero parameters, so there is nothing for the description to explain and the baseline of 4 applies. No parameter-level ambiguity exists.

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 artifact (Closelooknet's Sovereign Pressure board) and enumerates its contents — G7 10Y/30Y yields, 10s30s and 2s10s slopes, per-country 2Y/10Y/30Y levels/changes, and a z-scored Pressure Index — so the agent knows exactly what data this returns. It doesn't explicitly contrast itself with neighbors like get_credit_stress or get_macro_regime, but the subject matter 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?

Usage is only implied: an agent can infer it should call this when sovereign-debt pressure is relevant, and the closing 'Daily.' signals the update cadence. There is no explicit when-to-use/when-not guidance and no alternative sibling (e.g. get_credit_stress) is referenced, leaving routing to inference.

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

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower; the description adds meaningful behavioral context by specifying end-of-day timing, engine-derived values, and the enumerated structural states (healthy leader / fragile / distribution / decoupling). It does not mention auth or rate limits, but for a read-only snapshot the disclosure is solid.

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 dense sentence, front-loaded with the resource and scope, followed by the returned fields and then the sibling pairing. Every clause carries information, though the long enumeration makes it heavier than strictly necessary.

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 correctly enumerates the returned fields and their sub-components, which is exactly what an agent needs to know what it will receive. For a single-required-param read tool this is close to complete; only return format details (e.g., structure of the trend changes) are left implicit.

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

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

Only one parameter (ticker) and schema description coverage is 100%, so the schema already documents the format and example. The phrase 'one covered stock' mildly constrains the ticker to the covered universe, but adds little beyond 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?

Specific resource (one stock) plus the exact scope of what is returned: Directional Flow trend score with 5/21/63-day changes, up/down-day beta with structural state, and index memberships. It also names the sibling tools it complements (get_price_history, get_signal_scores), so an agent can distinguish it from adjacent tools without opening schemas.

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

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

Explicitly frames the tool as the EOD snapshot to pair with get_price_history for bars and get_signal_scores for the quality panel, which tells an agent when this tool is the right one. No when-not-to-use or exclusion is stated, so it stops short of a 5.

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

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds real operational context beyond them: content is automated and disclosed as such, deterministic, newest-first, and only live Mon–Fri. It also specifies the card anatomy (headline, excerpt, body), which the annotations do not.

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 dense sentence followed by two short ones; the resource and its scope are front-loaded with no filler. It is slightly run-on, packing card types and schedule into one clause chain, but nothing is wasted.

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

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

With no output schema, the description compensates by describing the return shape (headline, excerpt, body), the ordering, and the update cadence, and defaults live in the schema. The only real gap is the absence of routing guidance against similar feed siblings.

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

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

Schema coverage is 100%, so the baseline is 3, but the description goes further by mapping domain language onto the coded parameters — session wraps to B1, macro/recap to B2, earnings/PEAD to C, outliers to D, and Asia/Europe/US/after-hours to the window values — making the enums interpretable in context.

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 resource (timestamped market cards) with an explicit content inventory — session wraps, macro prints, earnings reactions, outliers, PEAD signals, weekly recaps — and ordering (newest first). It does not, however, name or contrast any sibling such as get_wire or get_latest_view, which look like adjacent feed tools.

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 says what the surface contains and that it runs Mon–Fri live, but never states when to reach for it over alternatives like get_wire or get_latest_view, nor any exclusions. Usage is left entirely to inference from the content list.

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=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral context beyond that: refresh cadence ('Refreshed after each close'), data provenance (mirrors closelook.net/signals/board/ with a dated archive), and the fact that each card carries its own session and as-of date.

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?

It is front-loaded with the resource name and stays to three sentences, though the first sentence is a dense, somewhat promotional run-on mixing content categories with geography. No wasted sentences, but the marketing tone slightly dilutes the informational payload.

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 carries the burden of describing returns, and it does so at the category level (new highs, big moves, analyst-target gaps, rotation, cooling reads) plus refresh timing and provenance. It is complete enough to invoke correctly, though it does not specify the response shape or how sessions differ across cards.

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 both parameters (limit, region) are fully documented in the schema and the baseline is 3. The description only loosely gestures at the region dimension ('across the US, Europe and Asia') and adds no syntax, default, or filtering nuance 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 states a specific resource (the Tech Signal Board) and enumerates its content: new highs, big moves, analyst-target gaps, sector rotation and cooling reads across stocks, sectors and indices. An agent can tell what the tool returns, but it never differentiates itself from closely related siblings like get_signal_scores, get_ranking or get_mag_pulse.

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?

There is no when-to-use guidance, no exclusions, and no mention of any alternative tool. The agent is left to infer that this is the tech-focused board rather than one of the many other ranking/signal siblings.

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 readOnlyHint/openWorldHint/destructiveHint already covering the safety profile, the description adds real behavioral context: newest-first ordering, contents of each wire, refresh cadence ('several times per trading day'), and archive linkage. It stops short of auth or rate-limit details, so not a full 5.

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

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

Front-loaded with the two-wire split and dense with specifics; the archive and refresh sentences are short and earn their place. Slightly long overall but 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?

No output schema exists, so the description carries the return-content burden and does so by describing what each wire contains (calls, price-target moves, consensus EPS comparison, forward calendar). Missing only edge cases such as what an empty wire or invalid ticker returns.

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 baseline is 3, but the description adds semantic meaning to the wire enum beyond 'Which wire (default: analyst)' by spelling out exactly what data each value surfaces. limit and ticker are left 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?

States a specific verb+resource ('two US wires') and immediately disambiguates the two modes: wire=analyst is sell-side calls, wire=earnings is prints vs consensus. An agent can tell exactly what this returns without opening the schema.

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

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

The description clearly explains what each of the two wires delivers, which is the main selection decision for this tool. It gives clear context but no explicit when-not guidance or named alternatives among siblings like get_tape or get_latest_view.

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=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds value beyond that by disclosing the return shape (matching pieces with a one-line summary and link) and the corpus scope, though it says nothing about result limits or ranking behavior.

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

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

Two tightly written sentences: purpose and corpus inventory first, then the usage trigger. No filler and nothing redundant with the title.

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 two-parameter read-only search with no output schema, the description supplies the corpus scope, the return format, and the triggering use case. Nothing essential to 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 100% and the description adds no parameter-specific detail (no syntax or format hints for the query beyond what the schema's example already shows). Baseline 3 applies when the schema carries the parameter burden.

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

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

Names a specific verb (Search) and resource (Closelooknet's research corpus) and enumerates what the corpus contains — explainers, glossary, heresies, reports, strategy notes, finance library. No sibling tool is a search, so the agent can distinguish it immediately.

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 a clear use-case trigger ("what has Closelooknet written about X"), which sets context well. It stops short of naming alternatives or when-not-to-use cases, so it's short of the 5 bar.

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