whale-insights

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

The description discloses that 'updatedAt' reflects manual revision time, not request time, and that the data is cached for approximately 1 hour. This provides important behavioral context beyond a simple read operation, especially with no annotations present.

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

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

The description is extremely concise: two sentences that front-load the core purpose ('Airdrop tracker') and add key behavioral details. Every sentence earns its place with zero waste.

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

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

Given the low complexity (no parameters, no output schema), the description sufficiently explains what the tool returns and its caching behavior. However, the absence of an output schema leaves the exact format of the list undefined, 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?

There are no parameters. The input schema is empty with 100% coverage. Per guidelines, a tool with zero parameters receives a baseline score of 4, and the description appropriately adds no redundant 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 an 'Airdrop tracker' providing a 'curated list of active airdrop opportunities'. This distinguishes it from sibling tools like 'funding_rates' or 'liquidations', 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 usage for fetching airdrop opportunities, but does not explicitly state when to use or avoid this tool, nor does it mention alternative tools. The context is clear enough given the variety of siblings, but lacks direct 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 burden of behavioral disclosure. It explains pagination, the 1-year time window, and that it uses query parameters. It does not mention rate limits or authentication, but these are standard for data retrieval. The description adds value beyond the schema by explaining the variant and analyst ID mappings.

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 detailed but well-structured: a summary sentence, a note about the variant, a list of analyst IDs, and filter descriptions. It is front-loaded with the core purpose. Minor redundancy could be trimmed, but overall it is concise and informative.

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

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

Given the tool has 5 parameters, full schema coverage, and no output schema, the description explains the list of signals but does not describe the structure of an individual signal (e.g., fields like timestamp, content, outcome). This leaves some ambiguity about the return format.

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

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

Schema coverage is 100%, baseline is 3. The description adds significant meaning by providing a mapping for analyst IDs (e.g., 'chain_hawk (ChainHawk, BTC & macro on-chain)') and clarifying the period and outcome filters with examples. This goes beyond mere enum listings.

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

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

The description clearly states the tool returns a paginated archive of signals for a single analyst, covering up to 1 year. It distinguishes itself from siblings by specifying it's the MCP-tool-compatible variant and explicitly mentions pagination and analyst-specific filtering.

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 for when to use this tool (to access a single analyst's signal archive) and lists available analyst IDs and filters. However, it does not explicitly state when not to use it or compare with similar sibling tools like 'analysts_signals' or 'analysts_signals_all'.

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, description fully covers behavioral traits: returns only shortSummary, generation details, caching, rate limit, empty array before 9:00 UTC. Clearly a read operation with no destructive effects.

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

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

Concise single paragraph with clear structure: summary, generation, endpoint details, field list, caching, timing. Every sentence adds essential information without waste.

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 provided, but description explains all return fields, empty array case, rate limit, and caching. Highly complete for a zero-parameter 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?

Input schema is empty (no parameters), so schema coverage is 100%. Baseline 3 is appropriate; description adds no parameter info but correctly addresses output.

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

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

Clearly states the tool returns today's AI-generated daily commentary for all 10 analyst personas, with specific verb and resource. Distinguished from siblings like 'analysts' and 'analysts_signals' by focusing on daily summaries.

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?

Provides context on public access, timing (empty before 9:00 UTC), caching, and rate limit. Implies use for overview and mentions authenticated endpoint for full commentary, but lacks explicit when-not-to-use or alternative comparisons.

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 fully carries the burden. It details the 6-month window enforcement, the list of all 10 analysts always present, the data source (signal_history table), and null conditions for win_rate (fewer than 5 resolved signals) and avg_return (no resolved+priced signals). This is highly transparent.

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 thorough and well-structured, starting with a clear summary sentence. While it is somewhat long, every sentence provides necessary detail. Minor improvement could be making it slightly more concise, but it remains effective.

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

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

Given the absence of an output schema, the description comprehensively explains the return values: metrics, months, analysts list, null conditions, and data source. It covers all aspects needed for correct interpretation.

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 no parameters, so schema coverage is 100%. The description adds value by explaining the fixed scope (last 6 months) and data semantics, which goes beyond the empty schema. Baseline for 0 params is 4, and this is appropriate.

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

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

The description clearly states the tool returns a monthly performance summary for all analysts over the last 6 months, including specific metrics (win_rate, avg_return, total_signals). This distinguishes it from sibling tools like 'analysts' or 'analysts_signals' which likely provide different data.

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 explicitly mentions usefulness for answering questions like 'How did WhaleWatch perform in May?' or 'Who was the best analyst last month?', providing clear usage context. However, it does not explicitly state when not to use this tool or mention alternatives.

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

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

With no annotations, the description carries full burden. It discloses that analysts are algorithmic identities, stats are computed live from PostgreSQL, and explains the format of winRate and avgReturn. No side effects or destructive behavior are mentioned, but it's a read-only 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 fairly detailed but ends abruptly with 'B', suggesting truncation or a typo. This reduces clarity and professionalism. The first sentence front-loads the purpose, but the overall structure is marred by the incomplete ending.

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

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

Given no output schema, the description adequately explains return values (10 analysts with stats) and the filter. It covers essential information, though the truncation may leave some uncertainty. For a simple list tool, it is largely complete.

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

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

Schema coverage is 100% (1 parameter described in schema). The description adds meaning by explaining the optional analyst filter's effect and the format of return fields (winRate as fraction, avgReturn as percentage), which goes beyond the schema.

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

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

The description clearly states that the tool returns all 10 analyst personas with live performance stats. It lists each analyst's name and domain, making the purpose highly specific and distinct from sibling 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 explains what the tool does (returns all analysts or a filtered one) but does not explicitly state when to use it versus alternatives like analysts_signals or analysts_top. Usage is implied but not guided.

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

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

No annotations provided, so description carries full burden. It explains free-tier depth (last 7 days, up to 200 signals per analyst), no auth needed, and response format. Does not mention rate limits, but for a free-tier read endpoint, this is sufficient.

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?

Description is detailed but front-loaded with key info, well-structured with examples. A bit lengthy but every sentence adds value.

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

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

Given no output schema, description explains response format for both single and multi-id requests, including sample signal structure. With many sibling tools, it provides enough context for correct usage.

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 (id) with 100% schema coverage. Description adds much meaning: how to use single vs comma-separated, lists valid analyst ids with descriptions, and explains effect on response format.

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

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

The description clearly states the tool returns analyst signal history for the last 7 days, for single or multiple analysts, using specific verbs and resources. It distinguishes from sibling tools like analysts_signals_all.

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 states when to use this tool (last 7 days, single or multi-analyst) vs alternatives (use analysts_signals_all for all 10 at once). Also mentions no authentication required.

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

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

Discloses free-tier depth (7 days, 200 signals), no auth, no params, and response structure, but does not mention edge cases like empty responses.

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?

Packs a lot of information efficiently, but could be more structured with bullet points; still no wasted 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?

Fully compensates for lack of output schema by detailing response shape and fields; complete for a simple read tool with no parameters.

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 zero parameters and schema coverage 100%, the description confirms no parameters are needed, which is sufficient for this case.

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

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

The description clearly states it returns the last 7 days of signals for all 10 analysts in a single response, distinguishing it from siblings like analysts_signals and analyst_archive.

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 says when to use (cross-analyst comparison) and when not to (subset via alternative endpoint with specific parameter), providing a direct alternative.

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

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

No annotations provided so description carries full burden. Discloses return structure (analyst or null), ID-to-name mapping, meaning of winRate and avgReturn, 7-day window, and ~10min cache. Does not explicitly state read-only but implied; no destructive actions mentioned.

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?

Concise and front-loaded with main purpose. Every sentence adds value without redundancy. Covers purpose, usage, return details, and caching in a compact manner.

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

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

Given no output schema, description explains return value, null case, ID mapping, and field interpretations. Mentions caching. Slightly lacks details on exact fields of returned analyst object, but sufficient for a zero-parameter 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?

No parameters (baseline 4). Description adds context on output format, return conditions, and field meanings beyond schema. Schema coverage is 100% (no params), so description compensates well.

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

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

Clearly states that the tool returns the top-performing analyst (highest win rate with >=5 resolved signals) plus their last 3 recent signals. Specifies the resource and verb, and distinguishes from siblings by noting it avoids iterating over all 10 analysts.

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?

Explains when to use (to surface best signal source without iterating) and implies when not to (if all analysts needed, use sibling tools). Describes condition (5+ signals) and fallback (null). Lacks explicit alternative names but context is clear.

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

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

No annotations provided, but description fully discloses behavioral traits: no auth required, 60 req/min rate limit, maximum 90 days, return field list, and that only shortSummary is returned. This is comprehensive.

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?

Description is concise yet packed with information. Sentences are front-loaded: main purpose first, then query modes, restrictions, fields, auth, and rate limit. No redundancy, every sentence adds value.

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

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

Given zero parameters and no output schema, the description is quite complete. It covers usage, limitations, auth, rate limits, and fields. Minor gap: pagination mechanism (e.g., page token, limit) is not explained, but overall sufficient.

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?

Input schema has zero parameters, so baseline is 4. Description adds meaning by detailing query parameters (date, analystId, days) and their usage, but does not specify data types or default values, keeping it at a solid 4.

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

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

Description clearly states it returns paginated history of daily AI analyst summaries with specific query modes (by date or analystId+days). However, it does not explicitly differentiate from sibling tools like analyst_daily_summary or analyst_archive, so a score of 4 is appropriate.

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?

Provides clear context for usage: query by date or analystId with days, maximum 90 days, and shortSummary only. Does not explicitly say when not to use or list alternatives, but the context is sufficient for choosing 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?

With no annotations provided, the description fully discloses behavioral traits: data accumulates daily, entries older than 180 days are purged, no authentication required, 60 requests/min rate limit, 5-min in-process cache, and the exact response structure. There are no contradictions, and the description goes beyond basic purpose to cover performance and policy details.

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 moderately long (several sentences) but every sentence adds value: it states purpose, data content, example queries, response schema, usage limits, and caching. The structure is logical, starting with a bold summary and ending with technical details. It could be slightly more concise by removing the phrase 'MCP-compatible' which is implicit, but overall it is well-organized and not verbose.

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

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

Despite having no output schema, the description explicitly defines the full response structure: { days, history: [{date, opportunities: [{symbol, spreadPct, buyExchange, sellExchange, usdVolume}]}], total, updatedAt }. It also covers usage constraints (days parameter, rate limit, cache, auth, data retention). For a tool with one simple parameter and a need to explain the nested output, this description is comprehensive and leaves no obvious 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 100% coverage for the single parameter 'days', with a description that already provides default, minimum, maximum, and meaning. The tool description does not add substantial new information beyond confirming the default and max (7 and 180). It reinforces the schema but doesn't increase semantic understanding significantly, so a baseline score of 3 is appropriate.

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

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

The description clearly states the tool returns 'Historical arbitrage opportunities — top 5 per day', specifying the verb (returns), resource (daily top 5 cross-exchange opportunities), and distinguishes from sibling tools (none share this exact purpose). It explicitly mentions the data fields included (token symbol, spread, exchanges, volume) and the time granularity.

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 explicit usage guidance by giving example questions an AI agent might answer: 'which tokens appear most frequently in arbitrage?' or 'what is the average daily spread?'. It also specifies the query parameter (days) with default and max, and notes data is automatically purged after 180 days. However, it does not explicitly state when to avoid using this tool or mention alternatives, though the context is clear enough for basic use.

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

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

Full disclosure of behavior: archive never deleted, months with <5 records excluded, no authentication required, rate limit 60/min, 1-hr cache, and data source. No annotations provided, so description carries full burden and does well.

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?

Description is detailed but not overly verbose; each sentence adds value. Could be slightly more structured (e.g., bullet points) but remains clear and concise.

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

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

Since there is no output schema, the description comprehensively details the return fields (month, symbol, avgSpreadPct, etc.), exclusions, data source, auth, rate limits, and cache. Complete for a zero-parameter 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?

No parameters, so schema coverage is 100% and no additional parameter description needed. Baseline of 4 appropriate as there is nothing to improve.

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

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

Description clearly states the tool returns 'permanent monthly archive of cross-exchange arbitrage opportunities' aggregated from daily snapshots. It specifies the data structure and purpose for historical queries, distinguishing it from related tools like arbitrage_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?

No explicit guidance on when to use this tool versus alternatives like arbitrage_history. While the description implies use for monthly aggregated historical data, it does not mention sibling tools or provide usage context.

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

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

Discloses caching (~10min) and data source (LI.FI). No annotations, but description adequately covers behavioral traits for a read-only summary 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, front-loaded with core purpose, followed by important limitations. No wasted words.

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

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

Given no parameters and no output schema, description fully explains tool purpose and constraints (preview, caching). Sufficient for agent to understand what it does.

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

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

No parameters; baseline 4. Description adds meaning by specifying output content (recent large transfers and per-bridge summaries), compensating for empty 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?

Clearly states it provides cross-chain bridge flows with specific verb (bridge flows) and resource (recent transfers and per-bridge volume summaries). Differentiates from sibling tools like stablecoin_flows and whale_activity.

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?

Describes free preview limitations and subscription requirement for full history, implying usage for quick overviews. Lacks explicit when-to-use vs alternatives but provides sufficient context.

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

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

Without annotations, the description fully discloses behavior: caching (~5min refresh), subscription gating, and data sources. No contradictions or omissions.

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?

Succinct three-sentence description front-loaded with the tool's purpose, followed by key details (sources, preview limit, caching). No unnecessary words.

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

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

Given no output schema, the description adequately describes the return data (events with transaction links and volume history). It covers caching, sources, and access tiers, providing a complete picture.

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

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

No parameters exist; schema coverage is 100%. The description adds value by explaining the data returned (events and volume history), which is appropriate for a parameterless tool.

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

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

Description clearly defines the tool as a token burn tracker providing recent on-chain events and 14-day burn volume history. It specifies data sources (Etherscan, Blockchair, Solana RPC), distinguishing it from sibling tools like 'airdrops' or 'whale_activity'.

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 states the free preview limitation (top 3 events, full list requires subscription) and that data is cached with no per-request cost. Does not directly compare with alternatives but provides sufficient context for usage.

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

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

With no annotations, the description carries the full burden. It discloses a key behavioral trait: caching for approximately 5 minutes. This informs the agent about data freshness. However, it does not explicitly state that the tool is read-only or non-destructive.

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

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

The description is a single sentence that front-loads the tool's purpose and includes all essential information (what it returns, cache time). Every word is necessary and earned.

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

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

Given zero parameters and no output schema, the description is fairly complete, covering output components and cache behavior. It could additionally describe label ranges or update frequency, but the current information is sufficient for basic 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?

There are no parameters, and schema coverage is 100%. The description adds significant meaning by detailing the output contents (score, label, factors, history) beyond the empty schema, which has a baseline score of 4.

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

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

The description clearly states the tool provides a 'Fear & Greed index' with specific components: current score, label, contributing factors, and recent history. It distinguishes from siblings by specifying 'crypto Fear & Greed' and a '7-factor' index, which is unique among the sibling 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 implies usage for sentiment analysis but does not explicitly state when to use this tool versus alternatives like 'funding_rates' or 'market_heatmap'. No exclusions or context for when not to use are provided.

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

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

No annotations provided, so description carries full burden. It discloses DB-backed persistence, 5-min cache, and daily rows. Adequate for read-only tool, but could mention immutability or update frequency.

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?

Description is two sentences with a front-loaded noun phrase. Every sentence adds information: data content, source, usage, and caching. No wasted words.

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

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

For a simple historical data tool with one parameter and no output schema, description explains return type (score, classification, one row per day), source, and caching. Could be more explicit about update frequency, but otherwise 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?

Description adds meaning beyond schema by stating default 30 and max 180, but schema specifies maximum 90, creating a direct contradiction that could mislead the agent. The added value is undermined by inconsistency.

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

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

Description clearly states it returns daily historical Fear & Greed score and classification for the last N days, specifying source as platform's 7-factor composite index. Distinguishes from sibling 'fear_greed' which likely provides current index.

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

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

Description says 'Useful for trend analysis and AI agent context', implying usage, but does not explicitly state when to use vs alternatives like the sibling 'fear_greed' tool. No when-not 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 full burden and delivers: never deleted, grows indefinitely, aggregated from daily snapshots before purged, excludes months with <20 records, no authentication, 60 req/min rate limit, 5-min cache. This comprehensively discloses behavioral traits.

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 moderately concise, providing all necessary information in a few sentences. It is front-loaded with the main purpose, then details output structure, then constraints. Slightly verbose but not excessive.

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 no params and no output schema, the description is complete: it explains what the tool returns (including specific fields like avgScore, dominantClassification), the aggregation logic, exclusion criteria, rate limits, caching, and authentication. No gaps remain.

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

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

No parameters exist, so schema coverage is 100% trivial. The description adds full meaning about what is returned (avgScore, minScore, maxScore, etc.) and constraints (exclusion criteria). Baseline for 0 params is 4, and description provides sufficient 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?

The description clearly states it returns the permanent monthly archive of the Fear & Greed index, one row per calendar month, aggregated from daily snapshots. This distinguishes it from siblings like 'fear_greed' (likely daily) and 'fear_greed_history' (likely daily history) by emphasizing 'permanent monthly archive' and 'never deleted'.

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 explains when to use this tool: 'providing AI agents with macro sentiment context across months and years.' It details what is included and that months with fewer than 20 daily records are excluded. While it doesn't explicitly state when not to use it or compare to siblings, the purpose is clear enough for selection.

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

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

No annotations provided, so description carries full burden. Discloses pagination, fixed page size, max 30-day window, default behavior, and response structure. Lacks mention of rate limits or any potential restrictions beyond those mentioned.

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?

Well-structured: front-loaded summary then detailed breakdown. Some redundancy (repeats 'paginated 30-day history') but overall efficient and easy to scan.

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, but description provides response shape (items, total, page, pageSize, hasMore, updatedAt) and item fields (id, title, summary, source). Covers essential context for agent 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%, baseline 3. Description adds value by explaining defaults, example for q, meaning of each type, period options, and pagination indexing.

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

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

Clearly states it returns a paginated archive of crypto news, analysis, AI summaries from CryptoWhaleInsights, covering last 30 days. Explicitly excludes whale movement events, distinguishing from sibling tool whale_movements.

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?

Provides explicit guidance: whale movements excluded and directs to alternative tool; states AI agents can use without credentials; explains default filter and optional type filtering. When-not-to-use is clear.

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 fully bears the burden of behavioral disclosure. It clearly states the tool is read-only (no authentication required), non-destructive (never deleted), has rate limits (60 req/min), caching (5-min), data aggregation method (from daily snapshots before purge), and exclusion criteria (months with <20 records excluded).

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 concise, with every sentence providing essential information. It front-loads the main purpose and then adds details in a structured manner. No redundant or vague statements.

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 is no output schema, the description thoroughly explains the return fields (month, symbol, avgRate, minRate, maxRate, dominantSentiment, daysInMonth) and data quality constraints. It also covers authentication, rate limits, caching, and token coverage, making it complete for an agent to use 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 schema covers the single optional parameter 'symbol' with a description. The description adds value by explaining the default behavior (returns all top-10 tokens when omitted) and the effect of filtering, which goes beyond the schema's static description.

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

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

The description clearly states the tool returns the permanent monthly archive of perpetual funding rates, aggregated per token per month. It distinguishes from sibling tools like funding_rates and funding_rates_history by specifying 'permanent monthly archive' and 'never deleted', making the purpose distinct.

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 for monthly aggregated funding rate data, but does not explicitly compare with sibling tools like funding_rates or funding_rates_history. It mentions optional symbol filtering and coverage of top 10 tokens, which provides context, but lacks explicit 'when to use vs. alternatives' 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?

Discloses cache duration (3-min), meta fields for age and exchange count, which adds behavioral insight beyond a generic description.

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 concise sentences with key info front-loaded; no wasted words.

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

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

Lacks description of the output structure beyond meta fields; does not explain the sentiment label or the format of funding rates themselves.

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

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

No parameters, baseline 4; description adds no param info but none needed.

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

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

Clearly states it provides perpetual futures funding rates aggregated from three exchanges with a sentiment label, distinguishing from sibling tools that cover different metrics.

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 when-to-use or when-not-to-use guidance, but the description implies it's for funding rates; no alternatives 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?

With no annotations, the description fully discloses behavior: daily snapshots from three exchanges, cached 5min, cold-start days omitted, and details on sentiment calculation and interpretation. This is comprehensive and transparent.

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 lengthy but every sentence adds value, covering sources, tokens, output fields, sentiment, usage, and caching. It is front-loaded with the core purpose and well-structured, though slightly verbose.

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

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

Given no output schema, the description thoroughly explains the output (per-exchange rates, average, sentiment) and covers all relevant context (data sources, token list, time range, caching). It is complete for an historical data 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?

While the schema covers both parameters with descriptions and defaults, the description contradicts the schema on the 'days' parameter (description says max 180, schema says max 90). This inconsistency harms reliability and reduces the semantic value added.

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

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

The description clearly states it returns historical daily perpetual futures funding rates for a single token, specifying the time range, data sources, and supported tokens. It uses a clear verb 'Returns' and distinguishes from sibling tool 'funding_rates' by focusing on 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 provides default values, supported tokens, and an example query. However, it does not explicitly contrast with the sibling 'funding_rates' tool for current rates, leaving agents to infer the distinction from the name.

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

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

With no annotations, the description carries full burden. It discloses 30s caching, meta fields (cacheAgeSeconds, chainCount), and the scope of data. It does not mention authentication or rate limits, but for a read-only public data tool, these are less critical.

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?

Description is two sentences including cache details. Every sentence adds value: first defines purpose, second explains cache and metadata. 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?

For a parameterless tool with no output schema, the description fully explains what data is returned (fees, USD estimates, speed tiers) and metadata (cache age, chain count). No missing critical information.

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?

Input schema has zero parameters, and schema coverage is 100%. The description adds no parameter info since none exist. Baseline for 0 parameters is 4, and description meets it.

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

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

Description clearly states it retrieves current gas/transaction fees across 7 major networks with USD estimates per speed tier. The verb is implied (get/view), and it distinguishes from siblings like 'funding_rates' or 'liquidations' which are different fee types.

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

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

Description mentions cache behavior but does not provide explicit guidance on when to use this tool vs alternatives. It implies usage for gas prices but lacks when-not or alternative tool references.

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?

Despite no annotations, the description thoroughly discloses behavioral traits: derivation of severity from confidence scores, top tokens inclusion, data persistence via upsert every 5 minutes, omission of empty days, and 5-minute caching. This exceeds the minimum required transparency. However, note the input schema specifies max 90 while description says 180, creating inconsistency but not a contradiction with annotations.

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

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

The description is information-dense and well-structured with clear sentences. It could be slightly more concise (e.g., omitting backfill detail) but effectively communicates key behavior without excessive verbosity.

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

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

Given no output schema, the description adequately explains return fields (count, severity breakdown, top tokens), data source, update frequency, caching, and edge cases (empty days omitted). This covers all necessary context for an agent to understand the tool's behavior.

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% for the single parameter 'days'. The description adds context by restating the default and max, plus explaining its purpose as a look-back window. This adds value over the schema alone, though the max value discrepancy (schema 90 vs description 180) slightly reduces clarity.

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

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

The description clearly states the tool returns a daily summary of Golden Alerts for the last N days, specifying default and range. This is a specific verb-resource combination that distinguishes it from the sibling 'golden_alerts_snapshot' which likely provides current data.

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 explicit usage guidance by mentioning the 'days' parameter and its default/max values, but does not compare with alternative tools or state when not to use it. The context of daily summaries and backfilled data implies historical use, but a direct contrast with golden_alerts_snapshot would improve clarity.

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 reveals that the archive is permanent, never deleted, and grows indefinitely. It also states data source (signal_history database), no authentication required, rate limit (60 req/min), and cache duration (5-min cache). Additionally, it discloses that months with fewer than 20 daily records are excluded for statistical accuracy.

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 relatively long but well-structured and front-loaded with the core purpose. Each sentence adds value: purpose, aggregation context, field list, exclusion rule, data source, authentication, rate limit, and cache. Minor redundancy (e.g., 'permanent monthly archive' repeated) but overall efficient for the information provided.

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

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

Given the tool's simplicity (no parameters, no output schema), the description covers all necessary context: what it returns (field list with explanations), exclusion criteria, data provenance, authentication, rate limits, and cache behavior. This is fully sufficient for an agent to use the tool without additional information.

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?

There are zero parameters, and the input schema is empty with 100% coverage. According to the rubric, the baseline for 0 parameters is 4. The description adds no parameter information (none needed), but it enriches the tool's semantics by detailing the output structure, which aids agent understanding.

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

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

The description clearly states the tool returns a permanent monthly archive of Golden Alert activity, aggregated from daily snapshots. It specifies one row per calendar month and includes a list of fields. This effectively distinguishes it from sibling tools like golden_alerts_history (daily) and golden_alerts_snapshot (point-in-time).

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 long-term trend analysis by stating it provides AI agents with long-term trend data. However, it does not explicitly state when to use this tool versus alternatives like golden_alerts_history or golden_alerts_snapshot, nor does it mention when not to use it.

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 full burden. It thoroughly explains behavior: reads from cache, refreshed every 5 minutes, omits pro-only fields, maps severity, and describes response structure in detail. There is no contradiction with annotations.

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

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

The description is well-organized with a clear structure: purpose, behavior, omitted fields, alert types, severity mapping, and response format. It uses bullet points for readability, though it is somewhat verbose and could be slightly more concise without losing clarity.

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

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

Given the tool has no parameters and no output schema, the description is completely adequate. It provides full details of the response structure, alert types, severity mapping, and cache behavior, ensuring an agent can understand and invoke the tool correctly.

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

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

The input schema has no parameters, and schema description coverage is 100%. The description adds value by explaining the tool's purpose, but since there are no parameters, the baseline score of 3 is appropriate.

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

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

The description clearly states it returns the latest snapshot of Golden Alerts, up to 27 high-signal market alerts refreshed every 5 minutes. It specifies the resource (Golden Alerts) and the action (returns snapshot). It distinguishes from siblings by mentioning it's public and MCP-compatible, and the alert types are unique to this tool.

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

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

The description implies usage when you need the latest snapshot of Golden Alerts without triggering an AI query, but it does not explicitly state when to use this tool versus alternatives like analysts_signals. It provides some context (cache-based, no new query) but lacks clear exclusions or comparisons.

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

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

Discloses caching behavior (~5min) and scope (recent estimates by token), which are key behavioral traits. With no annotations, the description provides useful transparency beyond the schema, though it omits details like read-only nature or rate limits.

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

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

Single sentence of 7 words, extremely concise yet informative. Every word serves a purpose, with 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?

For a parameterless tool with no output schema, the description provides essential context: data type (liquidation map), recency (recent), granularity (by token), and caching behavior. No gaps for its simplicity.

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?

Zero parameters and 100% schema coverage make further parameter description unnecessary. The description adds no param details as none exist, so baseline 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?

Description states it provides recent market liquidation estimates by token, clearly indicating the data source and granularity. While it distinguishes from siblings like funding_rates or gas, it lacks an explicit verb.

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

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

No guidance on when to use this tool vs alternatives, nor any exclusions or prerequisites. The description merely states what the tool does without contextual usage 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?

Without annotations, the description carries the full burden. It discloses caching (~10s) and response fields ('meta.updatedAt', 'meta.cacheAgeSeconds'), but does not explicitly state read-only or safety. Good but not extensive.

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, front-loaded purpose, no wasted words. Efficiently conveys core behavior and response details.

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?

Adequate for a simple tool with no parameters, but lacks detail on what specific metrics are included ('counts' is vague). No output schema to compensate, so more context would help.

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

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

No parameters (0), schema coverage 100%. Description adds no parameter info, which is fine since none exist. Baseline 4 as per guidelines.

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 this tool provides 'live platform metrics' with 'real recent counts' and 'no fabricated floors', indicating a real-time snapshot. However, it does not explicitly differentiate from sibling tools like 'platform_stats', leaving some ambiguity.

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

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

No guidance on when to use this tool versus alternatives (e.g., 'recent_whales', 'whale_activity'). The description implies it's for live data but doesn't specify context or exclusions.

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

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

No annotations provided, but description thoroughly discloses: parallel queries to 8 sources, no authentication, date handling with fallback to monthly archive, metadata fields (resolution, dataCompleteness), caching policy, and rate limit (30 req/min). No contradictions.

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?

Eleven focused sentences; purpose and key behavior front-loaded. Every sentence adds value without redundancy. No fluff.

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

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

Given single parameter, no output schema, and no annotations, the description fully explains the tool's behavior: what data it aggregates, caching, rate limits, date range, fallback mechanism, and metadata fields. No gaps remain.

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?

Single optional parameter (date) with schema coverage 100%. Description adds significant context: format YYYY-MM-DD, defaults to today, max 730 days back, automatic fallback to monthly archive for dates >365 days old. Schema only provides type and format.

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

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

Description clearly states it's a 'Single-call aggregated market snapshot' for a given date, aggregating 8 specific data sources. This distinguishes it from sibling tools like fear_greed or funding_rates which provide individual metrics.

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?

Provides default date, max lookback (730 days), and no auth. However, it lacks explicit guidance on when to use this aggregated snapshot versus individual data source tools (e.g., if you only need Fear & Greed, use fear_greed instead).

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

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

With no annotations, the description adds valuable context: caching (~5min) and non-gated access. It does not disclose rate limits or error conditions, but for a read-only, zero-parameter tool, this is sufficient.

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 concise (one sentence plus two short phrases) and front-loaded with key information. Minor lack of structure (run-on) but no wasted words.

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

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

The description covers what the tool returns (metrics and sources), which is sufficient given no output schema. It does not mention limits or pagination, but as a single-view tool this is 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?

There are no parameters, so the schema provides complete coverage. The description adds meaning by detailing the output fields and data blending, which enhances understanding beyond the empty schema.

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

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

The description clearly states that the tool returns a market-wide token heatmap with specific metrics (volume, price change, market cap, chain) and data sources (CoinGecko top markets plus hidden-gems). This is precise and distinguishes it from sibling tools like fear_greed or funding_rates.

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

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

The description mentions it is non-gated and cached, implying general availability, but provides no explicit guidance on when to use this tool over alternatives. No exclusions or comparisons are given, leaving the agent to infer from the tool's purpose alone.

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

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

Discloses caching (~30 min), free preview limitation, and subscription requirement for full data. No annotations exist, so description provides good behavioral context despite missing rate limits or error 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 sentences with no fluff. Key information (purpose, examples, subscription, caching) is front-loaded and efficient.

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

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

Given no parameters or output schema, the description covers what the tool returns, caching, and access limitations. Additional details like update frequency or data source granularity could improve, but current is 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?

No parameters present; schema coverage is trivially 100%. Description adds value by explaining output structure (narratives with leading tokens) and access tiers, which is more than baseline 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?

Clearly states it provides trending crypto narratives (e.g., AI, RWA) with leading tokens, derived from CoinGecko Categories. Differentiates from sibling tools by focusing on narrative/theme-based data.

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

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

Implies use for narrative-based market insights, but no explicit comparison to alternative tools or when-not-to-use. Mentions free preview vs. full set, but lacks direct guidance on selection among 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?

Discloses caching behavior (~60s) and response contains updatedAt timestamp. However, no annotations exist, so description carries full burden; additional info like rate limits or authentication would raise score, but current details are adequate.

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 concise sentences covering purpose, content, caching, and response format. Zero waste.

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, but description sufficiently explains what the response includes (key metrics and timestamp). Complete for a stateless read tool given no complexity.

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

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

No parameters, so baseline is 4. Description doesn't need to add parameter info; it correctly focuses on the tool's output.

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

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

Description clearly states it provides platform statistics with a specific list of metrics (tracked wallets, chains, tokens, etc.), distinguishing it from sibling tools which are more specific (e.g., airdrops, bridge_flows).

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?

Implied usage as the canonical overview tool for platform metrics. While it doesn't explicitly state when not to use it, the context suggests it's for general stats, and siblings cover specific areas.

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

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

No annotations provided, so description carries full burden. It discloses caching behavior (10-min cache) and meta fields (cacheAgeSeconds, chainCount, signalCount). This is informative and adds value beyond the 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 efficient sentences. First sentence states purpose, second adds technical details. No wasted words, front-loaded.

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

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

Given no parameters and no output schema, the description explains the output's meta fields and the top-3 slice. It is sufficient for an agent to understand what to expect.

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

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

No parameters, so baseline is 4. Description does not need to add param details. It correctly focuses on what the tool returns.

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

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

The description clearly states the tool returns recent whale movements with explorer-verifiable references. It is specific about the resource (whale movements) and scope (across supported chains), but does not explicitly differentiate from the sibling 'whale_activity' tool.

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

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

No guidance on when to use this tool versus alternatives like 'whale_activity'. The description implies it's for recent data but lacks explicit context for selection.

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

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

No annotations provided, so the description fully discloses behavior: returns last 12 reports, no auth needed, cached 1 hour, rate limit 60/min, response structure with specific fields. This is comprehensive and transparent.

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?

Description is informative but slightly verbose (multiple lines). However, key info is front-loaded: it starts with the purpose and public nature. Could be trimmed but still effective.

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

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

Given no parameters, no output schema, and almost no annotations, the description provides complete context: what it returns, caching, rate limits, authentication, and relation to Pro content. Nothing missing for a simple index 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?

Input schema has 0 parameters, so description doesn't need to clarify param meaning. It adds value by explaining the tool's output and constraints. Baseline 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?

The description clearly states the tool returns a public index of weekly reports with titles, summaries, dates, and week covered. It distinguishes itself from sibling tools by specifying it's a public, no-auth endpoint for recent reports, unlike others like airdrops or analysts.

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 explicitly says AI agents can use this to inform users about recent report topics and dates without authentication. It also mentions full content is Pro-only elsewhere, providing context on what not to do. No explicit when-not-to-use or alternatives, but clear for its simple 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 fully covers behavior: data source (CryptoWhaleInsights engine, Stocktwits+CoinGecko+price-momentum), update frequency (once per day from 5-min cycle), cold-start omission, caching (5min), and score interpretation (0–100, bullish/bearish thresholds).

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?

Description is a single paragraph but well-organized, with purpose first, then details. It packs many facts efficiently, though could be slightly more structured with bullet points or separation.

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 2 parameters, no output schema, and no annotations, the description covers essential aspects: what it does, how to use, data source, limitations (cold-start), and score interpretation. It is fairly complete, though return format is not described.

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 covers both parameters with descriptions (100% coverage). Description adds value by providing an example query, listing supported symbols, and explaining the score range and meaning, going beyond 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?

Description clearly states verb 'Returns' and resource 'daily historical social-sentiment score for a single token over the last N days', with specific details about data source and scope. It distinguishes from sibling tools by mentioning its unique engine and daily snapshot format.

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

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

Description provides usage example and parameter details (symbol required, days optional 1–180), and mentions cold-start day omission. However, it does not explicitly state when to use this tool over siblings or when not to use it.

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 fully discloses behavioral traits: permanent storage (never deleted), aggregation before purge, exclusion of sparse months, no authentication, rate limit, caching, and specific row fields. No contradictions or hidden behaviors.

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 paragraph with no wasted words. It front-loads the core purpose, then efficiently covers scope, filtering, row fields, exclusions, auth, rate limits, and caching. Every sentence adds value.

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

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

For a simple read-only tool with one optional parameter and no output schema, the description is thorough: explains purpose, scope, filtering, row structure, data quality rules, authentication, rate limits, and caching. No important 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?

Schema coverage is 100% and both schema and description describe the single 'symbol' parameter similarly. The description adds no new information beyond what the schema already provides, so baseline 3 is appropriate.

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

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

The description clearly states it returns a permanent monthly archive of social sentiment per token, with one row per token per calendar month, aggregated from daily snapshots. It distinguishes itself from siblings like 'sentiment_history' and other monthly archives by specifying 'permanent', 'never deleted', and covering exactly 35 tracked tokens.

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?

Provides context on when to use (permanent monthly archive, optional symbol filter) and usage constraints (months with fewer than 20 records excluded, 5-min cache, 60 req/min). Does not explicitly mention alternatives or when not to use, but the purpose is clear enough to guide selection.

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 thoroughly discloses all behavioral traits: never deleted, covers all analysts, optional filter, row structure, exclusion of low-signal months, no authentication required, rate limit of 60 req/min, and 5-min cache.

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 front-loaded with the purpose and packs detailed information (row structure, exclusions, rate limits) into a few sentences. While slightly verbose, every sentence earns its place.

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

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

Given the tool's simplicity (1 optional parameter, no output schema), the description covers all necessary behavioral and semantic aspects, including row schema, exclusions, and caching.

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 sole parameter (analystId) is described in the schema with examples. The description adds value by indicating it's optional, providing an example query, and listing all possible analyst IDs.

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

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

The description clearly states the tool returns a permanent monthly archive of analyst signal performance, with one row per analyst per month. It distinguishes itself from siblings by emphasizing permanence, aggregation, and coverage of all 10 analysts.

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 context for when to use this tool (for permanent monthly aggregated data) and mentions that months with fewer than 5 signals are excluded. However, it does not explicitly compare to alternative sibling 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?

Without annotations, the description covers key behaviors: non-gated access, caching (~5min), no per-request AI cost, and tiering for full insights. It discloses that AI insight text is excluded, which is important. Could be improved by mentioning rate limits or update frequency, but current details are sufficient.

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, front-loaded with the tool's purpose and contents. Every sentence adds value: first explains output, second adds caching and subscription context. No redundant or vague 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?

Given no parameters and no output schema, the description covers the tool's purpose, cached nature, and tiering. It distinguishes from siblings by focusing on social sentiment. Could mention typical score range or label interpretation, but overall sufficient for a parameterless 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?

With zero parameters, baseline is 4. The description adds meaning beyond the empty schema by specifying the output structure (aggregate score/label + top 5 tokens) and caching behavior. It does not detail the format of score/label, but the core semantics are clear.

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

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

The description clearly states it provides a social sentiment summary with aggregate market-mood score/label and top 5 tokens by sentiment. It distinguishes from full per-token insights by noting exclusion of AI insight text, ensuring the agent understands exactly what the tool returns.

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 for quick social sentiment without AI cost, and mentions that full insights require a subscription. However, it does not explicitly state when to use this tool versus siblings like fear_greed or narratives, nor does it provide alternative tools for different needs.

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

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

No annotations exist, so description carries the full burden. It discloses a ~30-minute cache, which is a useful behavioral trait. However, it does not mention other traits like rate limits, authentication needs, or whether it is read-only (though 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?

Extremely concise: one sentence plus a cache note. No wasted words, front-loaded with the main purpose. Every sentence earns its place.

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

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

The description provides basic information (data type and source, cache time) but does not describe the output format or structure. Since there is no output schema, more details on the returned data would improve completeness.

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

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

There are zero parameters, so schema description coverage is 100%. The description adds no information about parameters, which is appropriate since none exist.

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

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

The description clearly states it provides stablecoin supply, mint, and burn data from DefiLlama. The resource and type of data are specific, and it implicitly distinguishes from sibling tools like bridge_flows or burn_tracker. The verb is implied but not explicit (e.g., 'retrieves').

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

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

No guidance on when to use this tool versus alternatives. It simply describes what it does without specifying context or exclusions. Sibling tools exist but no comparison 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?

The description explains data source, handling of cold-start days, meaning of output fields, signal classification, and caching. However, it contradicts the input schema by stating max 180 vs schema's max 90, causing potential confusion.

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 concise, front-loaded with the main purpose, and efficiently explains behavior without extraneous words.

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

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

The description covers output fields, caching, and usage, but does not explicitly state that the result is an array of daily snapshots, though it is implied.

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 description adds context for the 'days' parameter (default 30, max 180) but contradicts the schema which specifies max 90. This error undermines the added value, and the schema already has a 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 states it returns daily historical stablecoin net-flow and total supply, which is specific and clear. However, it does not explicitly distinguish itself from the sibling tool 'stablecoin_flows'.

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 context on the time window and cold-start omissions but lacks explicit guidance on when to use this tool versus alternatives like 'stablecoin_flows'.

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 fully discloses behavioral traits: it is never deleted, requires no authentication, has a rate limit of 60 req/min, and a 5-minute cache. It also explains that data is aggregated from daily snapshots before purge, providing complete transparency for a zero-parameter 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 fairly concise (four sentences) and front-loaded with key information. It could be slightly tightened, but every sentence provides useful detail without unnecessary 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?

Despite no output schema, the description lists all fields returned (totalNetFlow, avgTotalSupply, etc.) and explains aggregation details. Combined with the parameter-less input, it gives an AI agent complete contextual understanding of what the tool provides.

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?

There are zero parameters, so baseline is 4. The description does not need to add parameter semantics, and it appropriately focuses on the output.

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 explicitly states this tool returns a permanent monthly archive of stablecoin flow data, aggregated from daily snapshots. It clearly distinguishes itself from daily or other historical tools by specifying 'permanent monthly archive' and 'one row per calendar month'.

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 for long-term macro liquidity context and mentions it is never deleted, but does not explicitly state when to use this over siblings like stablecoin_flows or stablecoin_history. However, the context of 'permanent' and 'monthly' is clear enough for an AI agent to infer appropriate use.

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

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

Discloses caching (~30s) and lists return fields. Without annotations, it provides good behavioral context for a read-only status check.

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: first states purpose and return fields, second gives usage context and caching. No wasted words, front-loaded.

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

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

Given no parameters or output schema, description fully explains what is returned and when to use it, including caching behavior.

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

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

No parameters; schema coverage is 100%. The description adds no parameter info, but none needed. Baseline 4 for zero-parameter tool.

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

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

The description clearly states it returns API and system status, including overall verdict and per-source health. It distinguishes itself from sibling tools (all data retrieval tools) by focusing on platform health.

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 states it's useful for verifying platform is live before making requests, implying a prerequisite check. No alternatives or exclusions needed given uniqueness.

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 full burden. It clearly states the tool is a read-only reference ('Reference'), non-advice, and cached, which sufficiently discloses behavior for a simple lookup tool.

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

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

Two short sentences with no fluff. Each part adds value: purpose, jurisdictions, educational note, cache duration.

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

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

Given zero parameters and no output schema, the description covers purpose, scope, and caching. It lacks return format details, but for a simple reference tool this is acceptable.

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?

There are no parameters, so baseline is 4. The description adds no parameter info, which is expected and acceptable.

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

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

The description clearly states the tool provides crypto tax rates for reference, lists supported jurisdictions, and distinguishes it from sibling tools by specifying its purpose for the tax calculator.

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 notes the tool is educational only and not tax advice, and mentions a 1-hour cache, giving context for appropriate use. It does not explicitly contrast with siblings but the context makes it clear.

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 provides good transparency: it mentions a 5-minute cache, meta fields for cache age and token count, and the data sources. It does not cover rate limits or auth, but for a read-only snapshot tool, it is sufficient.

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, concise and front-loaded with the core purpose. Every sentence adds necessary information without fluff.

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

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

Given the tool's simplicity (no parameters, no output schema), the description covers data source, ranking, caching, and response metadata. It is complete for its complexity.

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 is empty, so the description adds all meaning. It explains the output structure (meta fields) beyond the schema, which is valuable. Baseline 4 for zero parameters is appropriate.

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

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

The description clearly states it provides trending tokens from DexScreener and CoinGecko, merged and ranked by 24h volume. It specifies the data source and ranking method, making the tool's purpose very clear.

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?

While the description explains what the tool does, it does not explicitly advise when to use it versus alternatives like market_heatmap or narrativas. The context is straightforward, but guidance on when to prefer this tool is missing.

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 fully carries the burden. It discloses caching behavior (served from cache, ~5min refresh), data sourcing (internal signal-history archive), and limitations (no USD volume, no wallet addresses, no per-transaction detail). This is highly transparent.

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 paragraph, but it is front-loaded with the main purpose and covers all key aspects (output, limitations, parameter usage, caching). It is concise and informative, though slightly more structure could improve scanability.

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

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

The tool has one parameter and no output schema. The description explains the output format (counts grouped by chain, direction, day) and explicitly states what is not returned. Given the tool's simplicity, this is complete and sufficient for an agent to understand the response.

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% for the single parameter 'window'. The description adds minimal extra info (clamping behavior) beyond the schema's documented range and default. Baseline 3 is appropriate as the schema does the heavy lifting.

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

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

The description clearly states the tool returns aggregated historical whale activity counts across 14 chains, grouped by chain, direction, and day. It explicitly distinguishes what is included and what is not (no per-transaction detail, no wallet addresses, no USD volume). This is specific and differentiates from 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 explains when to use this tool for aggregated counts and notes that detailed data is subscriber-gated elsewhere. It provides guidance on the window parameter and its range. While it does not explicitly compare to all siblings, it gives sufficient context for appropriate use.

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

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

With no annotations, the description fully discloses behavioral traits: data written via 5-minute cron upsert, today's row current, rows older than 365 days purged, results cached for 5 minutes. No contradictions with annotations (none provided).

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?

Every sentence adds value, starting with the core function and followed by output details, data handling, caching, and example questions. No wasted words.

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

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

Despite no output schema, the description enumerates all return fields (total_moves, total_usd_value, etc.), explains data freshness, purging, and caching. Complete for a tool with one parameter.

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 covers 100% of parameters, and the description adds usage context (default 30, max 180) but contradicts the schema maximum of 90. This inconsistency reduces clarity.

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 explicitly states the tool returns daily aggregated whale movement counts over the last N days. It distinguishes itself from siblings like 'whale_movements' and 'recent_whales' by focusing on daily summaries with specific fields.

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 guidance on when to use it (for daily aggregation, adjustable look-back via days parameter), mentions caching and data freshness. However, it doesn't explicitly exclude real-time queries or name direct alternatives.

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

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

With no annotations provided, the description fully bears the burden of behavioral disclosure. It details persistence (never deleted, indefinitely growing), aggregation, directional breakdown, exclusion condition, data source, authentication (none), rate limit (60 req/min), and cache (5-min). No contradictions.

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 moderately long but every sentence adds value. It front-loads the key purpose and efficiently packs details about fields, source, auth, rate limit, and cache. Could be slightly tighter but is well-structured.

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

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

Given no output schema and no parameters, the description is highly complete. It explains return fields, aggregation logic, exclusion rule, data source, authentication, rate limit, and caching. No obvious gaps remain.

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?

There are zero parameters, so the baseline is 4. The description adds no parameter information, which is appropriate as none exist.

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

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

The description clearly states the tool returns a permanent monthly archive of whale movement activity, aggregated from daily summaries. It distinguishes itself from siblings like whale_daily_summary by emphasizing historical persistence and monthly aggregation.

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 explicitly says the tool answers historical questions (e.g., 'in which month were whale movements highest?') and notes exclusion of months with <20 daily records. It implies use for historical queries but does not explicitly state when not to use it or list 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?

Without annotations, the description bears full responsibility. It discloses pagination, 1-year limit, no-auth access, omitted explorerUrl, supported chains/directions, and keyword search behavior. However, it mentions a minUsd filter that does not appear in the input schema, which is misleading. It also does not specify rate limits, sorting order, default page size, or response structure, leaving gaps for an agent.

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 front-loaded with the most important traits (public, paginated, 1-year, no-auth). However, it is somewhat verbose, repeating the list of chains and including a dangling USD filter example. Some sentences could be merged or removed (e.g., the list of chains appears twice). The structure could be tighter without losing 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?

Given the tool has 5 parameters with 100% schema coverage but no output schema, the description provides useful context for all parameters including examples. However, it fails to specify output format (e.g., pagination metadata, default page size), error handling, or how to interpret results. The missing minUsd parameter is a notable gap. Overall, it covers basic usage but leaves significant questions for an agent.

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

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

Schema coverage is 100%, so the schema already describes all parameters. The description adds value with examples (e.g., q=USDT, q=ETH+Whale+%237) and enumerates chain/direction options again. However, it introduces a parameter (minUsd) not present in the schema, creating inconsistency that could confuse an agent. Overall, it adds marginal context but not enough to elevate beyond baseline given the schema completeness.

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

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

The description clearly states it returns a paginated archive of large whale on-chain movements, specifying it is the public, unauthenticated counterpart to another endpoint. It explicitly identifies the resource (whale movements), the action (archive/paginated retrieval), and the scope (14 chains, 1-year history). This distinguishes it from siblings like 'recent_whales' or 'whale_activity' by noting the auth-free access and historical depth.

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 explicitly states this is the public, unauthenticated version, guiding agents to use it when no credentials are available. It notes that it omits the explorerUrl field (Pro-only), setting expectations for data completeness. However, it does not explicitly list situations when not to use it (e.g., for real-time data, use 'recent_whales') nor mention alternative tools for authenticated access.

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