whale-insights

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

With no annotations, the description carries full burden. It discloses caching (~1hr), update semantics (manual revision reflected in updatedAt), and that entries are hand-verified. It implies a read operation but does not explicitly state read-only or auth requirements. Key behavioral traits are covered.

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

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

The description is two concise sentences: a clear front-loaded purpose statement followed by essential behavioral details (caching, update semantics). Every sentence adds value, no redundancy or 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 no parameters, no output schema, and no annotations, the description provides key context: what the tool returns (airdrops with chain/status/eligibility), curation quality (35 hand-verified), and behavior (cached ~1hr, manual updates). Lacks explicit output format but is sufficient for decision-making.

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 schema coverage is trivially 100%. According to guidelines, 0 params yields a baseline of 4. The description adds no parameter info because none exists, which 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 verb 'Get' and the resource 'curated active and upcoming crypto airdrops', specifying it's hand-verified and includes chain, status, and eligibility info. It distinguishes itself from 50+ sibling tools, none of which focus on airdrops.

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

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

The description implies the tool is for retrieving airdrop opportunities, but does not explicitly state when to use it over alternatives or when not to use it. Since it is the only airdrop tool, the lack of exclusion is acceptable but still lacks explicit 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. It discloses pagination, time window, query-param usage, and analyst options. Missing details on error handling, authentication, or response format, but covers the main behavior adequately.

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 and front-loaded with purpose. Every sentence adds value, though the list of analyst IDs could be slightly more compact. Overall 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?

No output schema is provided, yet the description does not describe the response format (returned fields, pagination metadata). Given the complexity (5 params, enums, pagination), this is a notable gap.

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

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

Schema coverage is 100%, so baseline is 3. The description adds some context (list of analyst specialties, period meaning) but mostly duplicates schema info. Marginal added value.

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, with a max 1-year window. It distinguishes itself as the MCP-compatible variant using query params, differentiating it from non-MCP counterparts.

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 single analyst signals via query params) and provides valid analyst IDs and filters. However, it does not explicitly compare to sibling tools like analysts_signals or analysts_signals_all, nor state 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, description provides extensive details: generation timing (9:00 UTC), model used (gpt-4o-mini), data sources (signals, Fear & Greed, BTC trend), caching (30 minutes), rate limit (60 req/min), and empty response before generation time.

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 comprehensive but somewhat long; front-loading the key purpose and then providing details is effective. Could be slightly more concise but all information is relevant.

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 fully covers behavior, data fields, generation details, caching, rate limits, and edge cases (empty before 9:00 UTC). Complete for agent decision-making.

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 in schema; description adds value by explaining what the tool returns (fields per analyst) and the structure, which is needed since schema has no properties.

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 today's AI-generated commentary for all 10 analysts with specific fields (signal count, confluence score, BTC trend). Distinguishes from sibling tools like analyst_archive and mentions a Pro endpoint for full commentary.

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 public endpoint with no authentication, mentions caching, rate limit, and behavior before 9:00 UTC. However, does not explicitly state when to avoid this tool or suggest alternatives for other 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 provided, so description carries full burden. Describes time window enforcement, data source (signal_history table), handling of missing analysts (empty array), and null conditions for win_rate and avg_return. 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?

Well-structured with front-loaded purpose and detailed behavior. Slightly verbose but every sentence is 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 no parameters and no output schema, the description fully covers input, output shape, constraints, and edge cases. Complete for a query 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 baseline is 4. Description adds significant value beyond the empty schema: explains fixed time range, mandatory analyst list, and null behavior.

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

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

Uses a specific verb ('returns') and clear resource ('monthly performance summary for all analysts'). Distinguishes from sibling tools like analyst_daily_summary by specifying monthly aggregation over exactly 6 months.

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 use cases ('How did WhaleWatch perform in May?' or 'Who was the best analyst last month?'). Does not explicitly list when not to use or compare to siblings, 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?

The description explains that stats are live, computed from signalHistory, and clarifies the format of winRate and avgReturn. It also notes that these are algorithmic identities, not human analysts, which is important behavioral context.

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

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

The description is overly verbose, listing all 10 analyst names and their domains, which could be summarized. Not every sentence is essential; the length may reduce readability.

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 (personas, stats format) and data source. It is fairly complete for the tool's purpose.

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

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

Schema coverage is 100%, so baseline is 3. The description adds minimal extra meaning beyond the schema's enum and description for the optional 'analyst' parameter.

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

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

The description clearly states the tool returns all 10 pseudonymous analyst personas with live performance stats. It also names each analyst, distinguishing from sibling tools that focus on signals or top performers.

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

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

The description does not provide explicit guidance on when to use this tool versus alternatives like analysts_signals or analysts_top. Usage context is implied but not explicitly differentiated.

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?

Fully describes constraints: public/free-tier, always last 7 days, up to 200 signals per analyst, no authentication. Also details response formats for both single and multi-ID requests. No annotations exist, so the description carries the full burden and meets it.

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 comprehensive but slightly verbose; every sentence adds value. Front-loaded with purpose, then usage, then details. Minor redundancy in listing analyst IDs both inline and in response format.

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 response structure for both single and multi-ID cases, including the signal fields. It also mentions limits and alternative endpoints, covering all necessary context.

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

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

Schema coverage is 100% for the single 'id' parameter, and the description adds valid analyst slugs and explains comma-separated usage, enriching beyond the schema's basic 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 analyst signal history for the last 7 days, supporting single or multiple analysts via comma-separated IDs. It distinguishes itself from sibling tools like analysts_signals_all (which fetches all 10 analysts at once).

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 explains when to use single vs. comma-separated IDs, and directs to an alternative (GET /api/public/analysts/signals/all) for fetching all analysts. No ambiguity about 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?

No annotations provided, so description fully bears the burden. It discloses free-tier limits (last 7 days, 200 signals per analyst), no authentication required, no query parameters, and the exact response shape. 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?

Description is comprehensive yet efficient. Every sentence serves a clear purpose: stating capability, ideal use case, analyst IDs, constraints, and response format. No redundancy.

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

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

Given no parameters and no output schema, the description fully explains the response structure (results, tier, updatedAt) and signal fields (id, tokens, typeLabel, etc.). An AI agent can confidently invoke and parse the result.

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 input parameters exist; schema coverage is 100% vacuously. The description adds all meaning by explaining the endpoint's behavior and response structure, which the empty schema does not provide.

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 all analysts' signal history in one request, distinguishing it from sibling tools like analysts_signals that likely fetch a single analyst. The verb 'returns' is specific.

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: for cross-analyst comparison without multiple round-trips. Also provides an alternative for subset fetching: use analysts_signals with ids. Clear 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?

Despite no annotations, the description fully discloses behavior: caching (~10min), return format with null case, mapping of analyst IDs to names, and field semantics (winRate as fraction, avgReturn as percentage). 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 thorough but not overly verbose. It front-loads key information and each sentence adds value. Slightly longer than necessary but still 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 and no output schema, the description provides complete context: conditions, return structure, caching, and field interpretations. No gaps.

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

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

No parameters exist, so baseline is 4. The description adds no param info, which is appropriate since schema coverage is 100% (empty object).

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 single analyst with the highest win rate, including specific fields (win rate, avg return, last 3 signals) and conditions (min 5 resolved trades). It distinguishes from sibling tools like 'analysts' by focusing on top performance, making it easy for an agent to select.

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 identifies its use case: 'Useful for AI agents that want to surface the best-performing signal source without iterating over all 10 analysts.' It provides clear when-to-use guidance but lacks explicit when-not-to or alternative tool mentions.

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 key behaviors: no auth required, 60 req/min rate limit, pagination implied, maximum 90 days, and lists fields in response. Lacks details on error handling but adequate given no 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?

Well-structured with bullet-like clarity, though slightly verbose. Front-loaded with main purpose and query options, but could be more compact.

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?

Covers return fields explicitly despite no output schema, distinguishes from sibling, and explains pagination implicitly. Reasonably complete for a history 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 zero parameters (coverage 100%), so baseline is 3, but description adds rich semantics: query parameters (date, analystId, days), format, maximum, and response fields, vastly exceeding schema.

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

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

The description clearly states the tool retrieves historical daily AI analyst summaries, specifying query options (by date or by analyst+days) and explicitly distinguishes from sibling analyst_daily_summary for today's 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?

Provides explicit guidance: use analyst_daily_summary for today's data, maximum 90-day query range, and notes that only shortSummary is returned (Pro-only for full commentary).

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?

Describes the 90-day window and minimum 3 resolved signals threshold. Lacks explicit read-only declaration (though implied), rate limit, or data freshness. Annotations absent, so description carries burden; adequate but not rich.

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?

Starts with summary but then includes a truncated sentence ('signals with a win/loss ou'), indicating incompleteness. Redundant analyst list included twice (in text and schema).

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

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

Truncation leaves output fields (token, total, resolved) incomplete. No output schema provided, so description should fully specify return format; it does not. Minimal for a simple query tool.

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

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

Schema covers analystId with enum and description. Description adds human-readable names and specialties (e.g., 'ChainHawk, BTC & macro on-chain'), enhancing usability.

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 top 5 tokens by win rate for a single analyst over 90 days. Differentiates from siblings like 'analysts_top' which likely returns top analysts, but does not explicitly contrast with analyst-specific siblings.

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

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

Provides valid analyst IDs but no guidance on when to use this tool versus alternatives like analysts_signals or analyst_monthly_performance. No when-not or 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?

With no annotations provided, the description fully discloses behavior: data accumulation, 180-day purge, response structure, rate limit (60 req/min), and 5-min cache. It gives a complete picture of what the tool does and its constraints.

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 comprehensive yet well-organized: front-loaded with purpose, then response shape, usage examples, and operational details. Every sentence adds necessary information without redundancy.

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

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

For a single-parameter tool with no output schema, the description is remarkably complete: it defines the response format explicitly, explains data scope and freshness, and covers caching and rate limits. 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?

Schema coverage is 100% with a clear description. The description adds value by showing the exact query syntax (?days=7), explaining the default and max, and linking the parameter to the daily history returned.

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 arbitrage opportunities (top 5 per day), specifies the data fields (token symbol, spread, exchanges, volume), and distinguishes from sibling 'arbitrage_monthly' by focusing on daily 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 context on when to use (e.g., answering questions about arbitrage patterns), mentions no authentication, and details the query parameter. It could be improved by stating when not to use (e.g., for real-time data or filtered queries).

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 excels: it explains the data structure (one row per symbol per month, columns), aggregation logic (excludes months with <5 daily records), persistence (never deleted, grows indefinitely), data source (CryptoWhaleInsights), authentication (none), rate limit (60 req/min), and cache (1-hr). This covers all behavioral traits an agent needs.

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 long but well-structured: it leads with the core purpose, then explains the data, use case, and constraints. Every sentence adds necessary detail. It could be slightly more concise, but for the complexity of the data, it is 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?

The description is fully complete for a parameterless tool. It covers what the tool returns, how the data is aggregated, persistence, use cases, data source, rate limits, and cache. 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?

The input schema is empty (0 parameters), so baseline is 4. The description adds extra value by explaining that the tool returns a fixed archive with no filtering options, and details the exact columns returned. This fully characterizes the parameterless invocation.

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 cross-exchange arbitrage opportunities. It uses specific language ('returns', 'permanent monthly archive') and implicitly distinguishes from sibling tools like 'arbitrage_history' by emphasizing monthly aggregation and permanence.

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 usage context by stating the archive is for answering historical questions like 'which token consistently had the highest arbitrage spread?' and explains it is aggregated from daily snapshots before they are purged. However, it does not explicitly state when not to use this tool or mention alternatives like 'arbitrage_history' for daily data.

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 disclosure. It transparently describes the data source (LI.FI API, 9+ protocols), caching behavior (5-min cache), and data retention (365-day table with permanent monthly archive). It does not mention authentication or rate limits, but the disclosed details are sufficient for a read-only data 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 four sentences long and front-loads the main purpose. While it includes some technical details (table names, retention), each sentence adds value. The structure is clear, but could be slightly more concise by removing internal table references.

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 fully explains what the tool returns (one row per day with specific fields), the data source, caching, and retention. Given the simplicity of the tool (one parameter, no output schema), it provides all necessary context for an agent to understand and use it correctly.

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

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

Schema coverage is 100% as the only parameter 'days' has a description in the schema. The description adds no new information beyond what the schema already provides, such as default value and range. Thus the description adds minimal semantic value beyond the schema.

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

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

The description clearly states it retrieves daily cross-chain bridge flow history, listing specific fields (volume USD, transaction count, protocol count, top protocol). It specifies the verb 'Get' and resource 'daily cross-chain bridge flow history' with a scope of up to 90 days. However, it does not explicitly distinguish itself from the sibling tool 'bridge_flows', which may cause slight 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?

The description mentions it is 'useful for tracking cross-chain capital flow trends', providing a general use case. It does not specify when to avoid using this tool or suggest alternatives, leaving the agent to infer appropriate usage without clear 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, so description covers behavioral traits: mentions caching (10min), free preview limits, and capital-rotation signal. Does not explicitly state authentication or rate limits, but given no annotations, this is fairly 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 somewhat repetitive, stating 'Recent large cross-chain bridge transfers' twice. It could be more concise. However, it is well-structured with clarifying clauses.

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

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

No output schema, so description should explain return values. It mentions 'top 3 flows + 2 bridge summaries' and volume summaries, but lacks detail on the structure or fields. Adequate but not 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?

Input schema has zero parameters, so schema coverage is 100%. Description adds value by explaining what data is returned without parameters. Baseline for 0 params is 4, and description fulfills 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?

The description clearly identifies the tool's purpose: retrieving recent large cross-chain bridge transfers, specifically mentioning Stargate Finance and Socket/Bungee via LI.FI. It distinguishes from siblings like bridge_flow_history by focusing on recent data and free preview limits.

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 for recent cross-chain bridge analysis, but no explicit guidance on when to use this tool versus alternatives like bridge_flow_history or stablecoin_flows. The subscription limit is mentioned, but not when to choose another tool.

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

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It discloses data sources (Etherscan, Blockchair, Solana RPC), caching behavior (~5min cache), and the subscription model (free preview vs. full list). It also mentions that events are on-chain and explorer-verifiable. It does not mention rate limits or authorization, but for a read-only cached tool, the disclosure is quite transparent. The description goes beyond the minimum by explaining the caching and preview limitations.

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

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

The description is slightly verbose but packs useful information into a few sentences. It front-loads the purpose in the first clause and then adds details on sources, limitations, and caching. It could be more concise by avoiding repetition (e.g., 'Etherscan + Blockchair + Solana RPC' mentioned twice), but overall it is well-structured and readable.

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

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

Given that there is no output schema, the description should explain the return format thoroughly. It describes the output as 'recent on-chain token burn events (with explorer-verifiable tx) plus a 14-day daily burn-volume history,' which gives a high-level structure. However, it lacks specifics about the fields of each event (e.g., token, amount, timestamp, transaction hash). For a simple tool with no parameters, a bit more detail on the output format would improve completeness.

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

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

The input schema has zero parameters, so schema description coverage is 100%. There are no parameters to document, and the description does not need to add meaning beyond the schema. The baseline for 0 parameters is 4, and the description provides context about what data is returned (events and history) without needing to explain parameters.

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

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

The description clearly states the tool retrieves token burn events and 14-day burn history for ETH, SOL, and BNB from specified sources. It uses a specific verb ('get') and resource ('burn events and history'), making the purpose clear. However, it does not explicitly differentiate from sibling tools like 'airdrops' or 'whale_activity', so it loses a point for lacking explicit sibling distinction.

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 includes usage context: a free preview of the top 3 events, full list requiring a subscription, and cached data with no per-request AI cost. This tells the agent when to use it (for burn data) and hints at limitations, but it does not explicitly state when to use this tool versus alternatives (e.g., whether to use this or 'trending' for other metrics). Guidance is present but not fully explicit compared to a 5.

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

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It discloses the data composition (score, label, factors, history) and caching behavior. However, it does not explicitly state that the tool is read-only or idempotent, though this is implied.

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

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

The description is two sentences long with no wasted words. It front-loads the main purpose and includes essential details efficiently.

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

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

With no parameters, no output schema, and low complexity, the description covers all necessary information: what the tool returns, caching cadence, and relationship to sibling tools. It is fully adequate for an agent to understand and use the tool.

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

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

There are no parameters, and schema description coverage is 100%. The baseline for zero parameters is 4. The description does not need to add parameter information, and it does not detract from 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 it retrieves the Crypto Fear & Greed index, listing key components (score, label, 7-factor breakdown, recent history). It explicitly distinguishes from the sibling tool 'fear_greed_monthly' by mentioning long-term trends, making the purpose specific and 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 provides explicit usage guidance by directing users to 'fear_greed_monthly' for long-term trends, helping agents choose the correct tool. It also notes caching (~5min), which is relevant for usage decisions.

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

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

No annotations are provided, so the description carries the full burden. It discloses the data source (7-factor composite index), caching (5-min cache), and DB-backed storage. It implies read-only data retrieval but does not explicitly state safety; the nature of the tool (historical data query) makes that implicit.

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 concise but contains some redundancy (e.g., repeating 'daily historical Fear & Greed score and classification'). It front-loads key information (score range, label) and is well-structured with a dash for sibling note.

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

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

With no output schema, the description explains the return format (score and label per day) and data source. It mentions applicability for trend analysis and AI context. However, it lacks precise details on the JSON structure or sample output, which would enhance 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?

The schema coverage is 100%, but the description states 'max 180 days' while the input schema's 'maximum' field is 90, an inconsistency that misleads the agent. The description adds minimal value over the schema, and the contradictory range undermines reliability.

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

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

The description clearly states the tool retrieves daily Fear & Greed score history with score and label per day for up to 180 days. It distinguishes itself from sibling 'fear_greed_monthly' by directing users to that tool for 2-year trends, ensuring the purpose is specific and unique.

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 advises using 'fear_greed_monthly' for longer-term analysis (2-year trends), indicating when not to use this tool. It also mentions default and maximum days, providing clear usage context. However, it does not exhaustively list all 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 fully discloses behavioral traits: never deleted, grows indefinitely, months with <20 daily records excluded, no authentication required, rate limits (60 req/min), and 5-min cache. 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 concise with no wasted sentences. It front-loads purpose, then details returned fields, exclusions, and access constraints. Each 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 parameters and no output schema, the description completely covers what the tool returns (fields like avgScore, minScore, etc.), exclusions (months with <20 days), and operational details (auth, rate limit, cache). An agent can use it without ambiguity.

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 0 parameters and schema coverage is 100%, so the description does not need to add parameter meaning. Baseline 4 is appropriate as the schema fully covers the parameterless interface.

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 with one row per calendar month, aggregated from daily snapshots. It distinguishes from siblings by emphasizing permanence and monthly aggregation, unlike daily fear_greed or fear_greed_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 usage context by mentioning it provides macro sentiment context across months/years and that daily snapshots are purged. However, it does not explicitly state when to use this tool vs alternatives like fear_greed or fear_greed_history.

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 pageSize=20), max period=30d, no credentials needed, and response structure. However, does not mention rate limits or other potential side effects. Still, adequately transparent for a read-only feed.

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 with clear sections and bullet points. However, some redundancy (first line repeats the purpose stated in the second sentence). Overall informative without being excessively 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 no output schema, description details the response fields (items, total, page, pageSize, hasMore, updatedAt) and each item's structure (id, title, summary, source). Distinguishes from many sibling tools. Covers all essential aspects.

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

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

Schema coverage is 100% with good descriptions. Description adds extra context: explains default for type filter ('all non-whale-move items'), case-insensitive matching for q, fixed pageSize, and period max window. Adds meaningful value 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?

The description clearly states it returns a paginated archive of crypto news articles, analysis, and AI-generated summaries. It explicitly distinguishes from sibling tools like whale_movements by noting whale events are excluded and directing to another endpoint. The verb 'Returns' and resource 'crypto news feed' are specific.

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 when-to-use: 'AI agents can use this to read the latest crypto news...without any credentials.' Also gives when-not-to-use: whale movements should use /api/public/whale-movements. Details optional filters (type, keyword, page, period) and their defaults.

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 discloses key behaviors: the data is never deleted, covers only top 10 tokens, excludes months with fewer than 20 records, and includes rate limits and caching. This is thorough given no annotations are 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?

The description is well-structured and informative, with each sentence adding value. It could be slightly more concise, but it remains clear and front-loads the core purpose.

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

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

Given the tool's simplicity (one optional parameter, no output schema), the description is complete. It explains the return fields, filtering behavior, exclusions, authentication, rate limits, and caching, covering all necessary context.

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

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

Schema description coverage is 100% for the only parameter 'symbol', so the baseline is 3. The description adds minimal new information about the parameter beyond what the schema already provides (just repeating the filter example).

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 perpetual funding rates per token, aggregated from daily snapshots. It distinguishes from sibling tools like funding_rates and funding_rates_history by emphasizing the monthly aggregation and permanent storage.

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

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

The description implicitly indicates usage by describing the data scope (monthly archive, top 10 tokens) and optional filtering. However, it does not explicitly state when not to use this tool or compare it to alternatives, leaving room for ambiguity.

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 data sources (3 exchanges), sentiment derivation, 3-min cache with exact age via meta field, and exchange count. No annotations provided, so description carries the 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?

Two sentences total, front-loaded with the main action, each sentence adds value without redundancy.

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

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

Given no parameters or output schema, the description covers key aspects: data sources, caching, and meta fields. Could specify output structure slightly more, but 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, so baseline 4 applies. Schema coverage is 100% trivially, and description adds context about output meta fields.

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 'Get live perpetual futures funding rates' with specific exchange sources and sentiment label, distinguishing it from sibling 'funding_rates_history' which is for historical 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 implies use for current rates via 'live', and context suggests alternatives like history tools exist, but no explicit when-not or alternative names are given.

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

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

With no annotations, the description fully discloses data sources, snapshot frequency, cold-start omission, caching, and sentiment interpretation. It covers behavioral traits thoroughly.

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 with front-loaded purpose. Slightly verbose but each sentence adds value. Minor redundancy in sentiment explanation could be trimmed.

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 thoroughly explains return fields (per-exchange rates, avg, sentiment label) and their interpretation, plus caching and omission details. Complete for agent use.

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

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

Schema coverage is 100%, so baseline is 3, but the description contradicts the schema on max days (description says 180, schema says 90), causing confusion. It adds token list and example query but the error outweighs benefits.

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 daily historical perpetual futures funding rates for a single token, with specific sources, top tokens, and fields. It distinguishes from siblings like funding_rates (current) and funding_rate_monthly (monthly).

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 a concrete query example (?symbol=BTC&days=30), defaults, supported tokens, and days range. Lacks explicit when-to-use vs alternatives but is sufficiently clear 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?

Discloses 30-second cache and meta fields (cacheAgeSeconds, chainCount) despite no annotations, adding useful behavioral context for a read-only operation.

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

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

Two sentences front-load the purpose and chains, then add caching details. Slightly verbose but efficient overall.

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 without output schema, the description adequately covers return values (fee estimates, speed tiers, meta fields), making it 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?

No parameters needed; description fully explains the tool's output (chains, USD estimates per speed tier) beyond the empty schema, meeting the baseline for zero-parameter tools.

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 fetches real-time gas prices across 7 specified chains with USD fee estimates, distinguishing it from sibling tools like gas_price_history.

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

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

Implies usage for checking current gas fees but lacks explicit guidance on when to use this tool versus alternatives 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?

No annotations exist, so the description fully carries the burden. It discloses DB-backed storage, 5-minute cache, 365-day retention with permanent monthly archive, and a 90-day max range, ensuring transparency about data freshness and 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?

The description is front-loaded with the core action and quickly lists supported chains. It is slightly verbose with retention details but remains focused and readable.

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 7 chains, multiple fee types, and no output schema, the description thoroughly explains the data returned (e.g., 'ETH fast gwei, ETH standard gwei...'), caching, and retention. It is complete for agent decision-making.

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 'days' parameter, and the description adds minimal context beyond the schema (e.g., '1–90, default 30' matches the schema's default and range). No significant additional meaning is provided.

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 specifies the tool retrieves daily gas price history across 7 blockchain networks with exact units (gwei, lamports). It is distinct from siblings like 'gas' (likely current prices) and other analytics 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 states it is 'useful for tracking gas fee trends and identifying high/low gas periods,' providing usage context. However, it does not explicitly state when to avoid using it or compare to alternatives like 'gas' for real-time data.

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 behavioral disclosure. It details persistence (ON CONFLICT DO UPDATE, 5-min cycle), data freshness (latest alert state at refresh), omission of empty days, and caching (5min). It does not mention destructive actions, which is fine for a read-only history 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?

Description is a single paragraph, front-loaded with purpose. Every sentence provides value (range, output detail, backfill info, update mechanism, caching). No wasted words; concise yet 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 no output schema, the description explains the output structure (total count, severity breakdown, top tokens). It also covers data source, update frequency, and omission behavior. For a list tool with one parameter, this is comprehensive.

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 days parameter. The description adds redundant usage syntax but no new meaning. Baseline of 3 is appropriate as the description does not compensate 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?

The description clearly states the tool returns daily summaries of Golden Alerts for a configurable look-back window. It specifies the resource (Golden Alerts history), action (returns), default/max days, and output breakdown. This distinguishes it from sibling tools like golden_alerts_snapshot (current snapshot) and golden_alerts_monthly (monthly aggregate).

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 how to use the days parameter and its range. However, it lacks explicit guidance on when to prefer this tool over alternatives (e.g., golden_alerts_snapshot for real-time vs. history for daily summaries). Usage context is implied but not contrasted with siblings.

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

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

With no annotations, the description fully discloses behavioral traits: permanent storage, indefinite growth, 20-record minimum, 60 req/min rate limit, 5-min cache, no authentication required. This exceeds expectations for a tool with no 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 front-loaded with the core purpose and is structured logically: purpose, fields, exclusion rule, data source, limitations. Every sentence adds value without redundancy, achieving high information density while remaining readable.

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 exhaustively lists return fields and explains the aggregation, exclusion criteria, rate limits, and cache duration. An AI agent has sufficient information to correctly invoke and interpret the tool's output.

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

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

The tool has no parameters, so the description does not need to describe any. According to guidelines, baseline is 4 for zero parameters, which is appropriate as the description adds no parameter info but also has no gaps.

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

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

The description clearly states that the tool returns a permanent monthly archive of Golden Alert activity, aggregated from daily snapshots. It lists specific fields (e.g., totalCount, highCount, mediumCount, lowCount, topTokens), distinguishing it from sibling tools like 'golden_alerts_history' and 'golden_alerts_snapshot'.

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 long-term trend analysis but does not explicitly state when to use this tool versus alternatives (e.g., golden_alerts_history). It provides context on exclusions (months with <20 daily records) and data source, which aids decision-making, but explicit alternatives are 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?

With no annotations, the description fully discloses behavioral traits: cache-based read, periodic refresh (5 min), omission of pro fields, severity mapping logic, and response shape. The cut-off 'No authentic' likely indicates no authentication, but is incomplete.

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, front-loading purpose and caching behavior. Every sentence adds value, though the length could be slightly trimmed. Well-structured with clear sections (types, severity, response).

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 comprehensively details the response format, including alert fields, severity mapping, and refresh timing. It addresses edge cases (null refreshedAt when cache empty). Covers all necessary context for a snapshot 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?

The tool has zero parameters, so the baseline is 4. The description adds value by detailing the output structure, alert fields, and severity mapping, going beyond what the empty schema provides.

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

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

The description clearly states the tool returns the latest snapshot of Golden Alerts, specifying sources (whale activity, volume momentum, Fear & Greed), alert types, and severity mapping. It distinguishes from history/monthly siblings by virtue of being a 'snapshot', though not explicitly naming alternatives.

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 (cache read, no AI query, public) but does not instruct when to use this tool vs alternatives like golden_alerts_history or golden_alerts_monthly. No when-not to use or exclusion criteria.

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

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

With no annotations, the description discloses important traits: DB-backed with 30-min cache, market-level aggregation, and exclusion of per-asset details. It does not explicitly state read-only behavior, but the context strongly implies it. 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?

Description is structured with a front-loaded summary then details. It is informative without excessive verbosity, though a few sentences could be combined. Still efficient and well-organized.

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 tool with one parameter and no output schema, the description is comprehensive: it explains input range, output columns, data source, caching, and scope limitations. No 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 covers the sole parameter 'days' completely (100% coverage with description). The tool's description adds no additional meaning beyond what the schema 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 the tool gets daily Leverage Radar market-level history with a specific list of fields (avg/max pressure, setup score, assets in critical zone, etc.). It distinguishes from siblings by noting 'Pro-only per-asset detail excluded — market-level only,' implying other tools handle per-asset 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 clear context for what the tool returns (market-level history) and hints at exclusions (per-asset detail), but does not explicitly name alternatives or state when not to use it. Usage guidance is implied but not fully explicit.

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: automatic saving, outcome resolution using live price data with specific win criteria, permanent record retention, and a 30-minute cache. This provides excellent transparency about how the tool operates.

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 dense with useful information and front-loaded with the main purpose. While it is somewhat long, every sentence contributes value. Minor redundancy could be trimmed, but overall 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 annotations, the description covers behavior, data freshness, limitations, and accuracy metrics. It provides enough context for an agent to understand the tool's purpose and output without needing 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 schema coverage is 100% (empty). The description adds context about the data source and aggregation, which is sufficient. Baseline for zero parameters is 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 that the tool gets a summary of Leverage Radar pick accuracy, including historical win rate, average return, and total pick counts. It specifies the data source (Best Trade Now picks) and distinguishes from related tools like leverage_history and leverage_radar by focusing on accuracy summary.

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

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

The description explains the context of when picks are saved (every 5 minutes on high-confidence setups) and limitations (full list is Pro-only), but it does not explicitly guide when to use this tool versus alternatives among the many sibling tools. Usage context is implied but not directly stated.

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

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

With no annotations, the description carries the full burden and does well: it discloses the tool is public and real-time, has a 5-min cache, returns pressure and setup scores, includes market summary and top setups, and notes Pro-only fields are stripped. It does not mention any destructive effects, which is appropriate. The only minor gap is not specifying rate limits or authentication needs (implied public).

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-structured with the main purpose front-loaded. It is relatively long but each sentence adds necessary detail (assets tracked, scores, market summary, pro-only stripping, caching, parameter). Could be slightly more concise by grouping related details, but overall efficient for the complexity.

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 complexity (50 assets, multiple scores, market summary, top setups, pro-only info, caching, window parameter) and no output schema, the description is remarkably complete. It covers what the tool returns (pressure/ setup scores, market summary components, top long/short setups, alerts), constraints (public, 5-min cache, pro-only stripped), and parameter usage. Nothing essential is omitted.

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

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

Schema coverage is 100% with one parameter 'window' having enum values, default, and description. The description adds value by explaining the trading windows as '1h (scalp), 4h (swing, default), 12h (position)', providing context beyond the schema's simple enum listing. This additional semantics justifies a score above the baseline 3.

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 gets a Leverage Radar snapshot with specific components (pressure scores, setup scores, top long/short setups, market summary) for 50 tracked assets. It uses a specific verb ('Get') and resource, and distinguishes from siblings like 'leverage_history' and 'leverage_picks_summary' by focusing on real-time snapshot.

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 obtaining current leverage data and mentions the optional window parameter with trading window definitions (scalp, swing, position). However, it does not explicitly state when to use this tool versus alternatives among the many siblings (e.g., for historical data vs. snapshot), nor does it provide exclusions or when-not-to-use 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 behavioral traits: 5-min cache, estimates not exact, data derived from price action and OI, georestrictions. No annotations provided, so description carries the burden 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?

Two sentences, efficiently front-loaded with the main action. Minor redundancy (repeats 'estimates' and 'leveraged-position liquidations'), but mostly 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?

For a tool with no parameters and no output schema, the description covers what it returns, caching, limitations (estimates, georestrictions), making it complete for 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?

No parameters; schema coverage 100%. The description explains what the output contains (liquidation amounts by token), adding meaning 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 uses specific verb-resource 'Get leveraged-position liquidation estimates' and distinguishes from siblings by focusing on liquidation amounts per token with caching and data sources.

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: useful for identifying tokens with high leverage risk and volatility triggers. Lacks explicit when-not or alternative tools, but the context is sufficient.

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, but description discloses caching duration, response fields (meta.updatedAt, meta.cacheAgeSeconds), and cache cold indicator. Adds meaningful behavioral context beyond a simple 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?

Three efficient sentences: first lists output contents, second clarifies caching, third details response meta fields. No redundant text.

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?

Cover all key aspects: output contents, caching, and important meta fields. Lacks explicit mention of time range ('today' implied) and exact structure of counts, but 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?

Schema has zero parameters with 100% coverage. Baseline is 4 for no parameters; description doesn't need to add param info. It adds value by explaining 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?

Clearly states it retrieves live activity counters for whale moves, smart-money wallets active, and golden alerts. Differentiates from sibling tools by specifying its real-time snapshot nature.

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 caching behavior (≈10s) and indicator of recency ('no fabricated floors'). Provides context for real-time use but does not explicitly mention when to avoid or suggest alternatives.

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

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

No annotations are provided, so the description must disclose behavior. It explains the fallback from daily to monthly archives for old dates, metadata fields like resolution and dataCompleteness, and caching for today. This adds significant behavioral context 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?

The description is somewhat detailed but front-loads the core purpose. It efficiently conveys key points without excessive verbosity, though some minor redundancy exists (e.g., repeating 'single-call aggregated market snapshot').

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 covers important return metadata (resolution, dataCompleteness) and caching behavior. For a tool with one optional parameter and a clear aggregation function, this is sufficiently 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?

The single parameter 'date' is fully described in the schema. The description adds value by clarifying default (today), maximum range (730 days), and automatic fallback to monthly data. This enhances understanding beyond the schema description.

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

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

The description clearly states the tool provides an aggregated market snapshot with explicit components (Fear & Greed, whale summary, etc.). It distinguishes itself from sibling tools that are individual endpoints by offering a single-call parallel query of 8 sources.

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 the tool is for getting aggregated market context in one call, with details on default date, maximum range (730 days), and fallback behavior for older dates. It does not explicitly state when to use alternatives, but the context is sufficient for an AI agent to understand its primary 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?

The description notes it is non-gated and cached ~5 minutes, which are helpful behavioral traits. However, with no annotations provided, it lacks details on rate limits, side effects, or whether the data is live or static. More transparency would be beneficial.

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, using two main clauses to convey purpose and content. It could be slightly more structured (e.g., separating metadata from output details), but overall it is efficient and avoids redundancy.

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

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

For a tool with no output schema, the description adequately explains the return values (list of tokens with specified fields). It lacks details on return format or pagination, but given the tool's simplicity, the coverage is 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?

There are zero parameters, so the description's job is to clarify the output. It explains the output includes top tokens by 24h volume with price change, volume, market cap, and chain, which adds value 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 it retrieves a token market heatmap ranked by 24h performance with volume, market cap, and chain details. It distinguishes itself from sibling tools like 'trending' by specifying it's a market-wide heatmap blending top and emerging coins.

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 a broad market overview with cache and no access restrictions, but it does not explicitly define when to use this tool over alternatives such as 'market_context' or 'trending'. No when-not criteria 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?

Despite no annotations, the description discloses that the data is DB-backed with a 5-minute cache and specifies data retention (365d, monthly archive). This provides useful behavioral context beyond the input schema.

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

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

The description is moderately concise but somewhat repetitive (e.g., 'Daily historical Market Pulse verdict and confidence' echoes the first sentence). It could be streamlined 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?

The description comprehensively lists the fields returned per row (verdict, confidence, Fear & Greed, regime, whale buy ratio, leverage suggestion) and includes cache and retention info. For a single-parameter tool without output schema, this is reasonably 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?

There is only one parameter (days) with schema description coverage at 100%. The description reiterates the range but adds no new syntactic or semantic details beyond the schema.

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

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

The description clearly states the tool retrieves daily Market Pulse history with specific data fields, making the purpose clear. However, it does not explicitly distinguish the tool from siblings like fear_greed_history or sentiment_history, which also provide historical market 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?

No guidance is provided on when to use this tool versus alternatives. The description lacks instructions on use cases, prerequisites, 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?

The description discloses data source (CoinGecko Categories), caching (5-min), retention policy (365d, permanent monthly archive), and row structure. With no annotations provided, the description adequately covers behavioral traits, though it lacks explicit read-only confirmation.

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 but packed with value, starting with a clear action statement, then details and context. It is not excessively verbose, though some internal implementation details (e.g., table name) could be omitted without loss.

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 compensates by detailing the output rows (market cap change %, strength score, token count, daily rank, top tokens). It covers data retention, caching, and filtering, making it complete for the tool's complexity (2 optional params, no enums).

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

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

Schema coverage is 100% with parameter descriptions. The tool description adds context by linking 'days' to 'over up to 90 days' and 'sector' to 'filter by ?sector= for a single sector trend', enhancing the schema's meaning.

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 'Get daily narrative/sector history' and specifies the content: top crypto market sectors ranked by market cap change %, strength, and token count. It distinguishes from sibling tools like 'narratives' (likely current) by focusing on historical daily 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 suggests the tool is 'useful for identifying which narratives are accelerating or fading' and mentions filtering by sector, but does not explicitly contrast with siblings or state when not to use it. Usage guidance is present but not comprehensive.

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 derivation (CoinGecko Categories), caching interval (~30min), and access limitations (free vs. subscription). No contradictions 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 relatively concise but slightly repetitive (mentions 'trending market narrative sectors' twice). Key information is front-loaded, and 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 parameters and no output schema, the description explains what the tool returns (top narratives and tokens) and limitations. However, it does not describe the output structure or format, which would be helpful for 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?

The tool has zero parameters, so schema coverage is 100% and the description adds no parameter detail. Per guidelines, baseline is 4 for no parameters, and the description does not need to compensate.

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

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

The description clearly states the tool retrieves top trending market narrative sectors with leading tokens, listing examples (AI, RWA, DePIN, memecoins) and specifying the data source (CoinGecko Categories). This distinctly differentiates it from siblings like narrative_history, which provides historical 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 does not explicitly state when to use this tool versus alternatives. It mentions the free preview limitation but lacks guidance on context or exclusions relative to similar tools like trending or market_context.

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

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

With no annotations, the description properly discloses caching duration and the presence of a timestamp. This is adequate for a read-only tool, but does not mention any authorization or other behavioral 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 short (two sentences) but slightly redundant, repeating 'canonical platform metrics'. It front-loads the main purpose and provides necessary details efficiently.

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 sufficiently explains what the tool returns and its caching behavior. No critical information is missing for a simple retrieval 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?

The tool has zero parameters, so the schema provides no signal. The description compensates by listing the exact contents of the response, adding meaning 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 the tool retrieves canonical platform metrics and enumerates the specific metrics included (tracked wallets, chains, win rate, BTC benchmark, etc.). It distinguishes from sibling tools by focusing on a broad aggregate overview.

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 caching behavior (~60s) and the updatedAt timestamp, implying the tool is for fresh data but not stale. However, it lacks explicit guidance on when to use this tool versus sibling tools like live_stats or market_context.

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

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

With no annotations provided, the description carries full burden. It discloses a 10-minute cache, directs users to check 'meta.cacheAgeSeconds' for freshness, and explains meta fields. This adds useful behavioral context beyond basic operation.

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

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

Every sentence adds distinct value: front-loaded with primary action, then sibling differentiation, then technical details (cache, meta fields). 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 output schema, the description partially compensates by mentioning meta fields and explorer references. However, it could more explicitly describe the structure of each whale transfer entry (e.g., fields like amount, token, chain, explorer link). Still, it's mostly complete for a simple 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?

There are no parameters, so baseline is 4. Description adds no parameter-specific info, but schema coverage is 100% vacuously.

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

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

The description clearly states the tool retrieves the latest 3 whale transfers as a live snapshot across 14 chains. It distinguishes itself from siblings 'whale_activity' and 'whale_movements' by specifying their different purposes (counts vs. paginated 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?

The description explicitly advises when to use alternative tools: 'use whale_activity for counts, whale_movements for paginated archive', providing clear usage context and exclusions.

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

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

No annotations are provided, so the description carries full burden. It discloses no authentication required, 1-hour cache, 60 req/min rate limit, response structure, and that full content is Pro-only via another endpoint. 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 well-structured, front-loading the purpose and then providing details on response format and usage constraints. Every sentence adds necessary information without redundancy.

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

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

With no output schema, the description fully covers the response shape, caching, rate limiting, authentication, and the distinction between public index and full Pro content. It is 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?

The input schema has zero parameters, so baseline is 4. The description adds value by detailing the response fields (id, title, summary, publishedAt, weekOf) and constraints (summary ≤300 chars, weekOf 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 it returns a public index of the last 12 weekly Alpha reports with titles, summaries, dates. It uses a specific verb ('returns') and resource ('weekly reports index'), and distinguishes itself from sibling tools (no other tool provides a public report 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?

The description indicates usage context: 'AI agents can use this endpoint to inform users about recent report topics and dates without any authentication.' It implies when to use but does not explicitly state when not to use 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?

Discloses data source, update frequency, cold-start omission, score interpretation, and caching. However, the description claims max 180 days while the schema says max 90, introducing a factual inconsistency that could mislead the agent. No annotations are present, so the description bears full burden.

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?

Efficient and well-structured: front-loaded with purpose, then details. Some redundancy (e.g., 'default 30, max 180' repeated), but overall each 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 2-parameter tool with no output schema, the description provides good context: explains output nature (score 0-100 with thresholds), data omission, and data source. Missing explicit output format but sufficient for agent understanding.

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). The description adds value by listing many supported symbols, clarifying symbol is required, and restating days range. The discrepancy in max days slightly reduces reliability.

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 the daily historical social-sentiment score for a single token over the last N days', clearly identifying the action, resource, and scope. It distinguishes from siblings like 'sentiment_monthly' by emphasizing 'daily snapshots'.

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 an example call ('?symbol=BTC&days=30') and clearly states symbol is required and days is optional with range 1–180. However, it does not explicitly compare to sibling tools or mention when to avoid 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, the description fully discloses behavior: data aggregation, permanent retention, token coverage, row structure, exclusion criteria, authentication requirements, rate limit, and cache duration. 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?

The description is well-structured, starting with the core purpose and then providing details in a logical order. Every sentence adds value; no redundant 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's complexity (monthly aggregation, exclusion rules, rate limits), the description provides all necessary information for an agent to use it correctly. No additional context is needed.

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

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

The schema covers 100% of the parameter, and the description adds practical context: how omission returns all tokens, and example usage. This adds value beyond the schema description.

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

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

The description clearly states the tool returns a permanent monthly archive of social sentiment per token, with specific aggregation and retention details. It distinguishes itself from sibling tools like sentiment_history by emphasizing the monthly granularity and permanent storage.

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 (for permanent monthly historical data) and how to filter by symbol. It does not explicitly contrast with alternatives, but the context makes usage scenarios obvious.

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 carries full burden. It discloses that the data is never deleted, covers all 10 analysts, includes specific fields, excludes months with fewer than 5 signals, requires no authentication, has 60 req/min rate limit, and 5-min cache. 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?

The description is a single sentence that front-loads the purpose and then enumerates details. It is clear but slightly dense; could be broken into shorter sentences.

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

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

With no output schema, the description fully explains the return fields (month, analystId, totalSignals, winCount, etc.). It also covers exclusion criteria, rate limit, cache, and authentication, making it complete for tool selection and 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% with parameter description already in the schema. The description adds value by providing an example value (chain_hawk) and clarifying that omitting the parameter returns all analysts.

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 lists the specific analysts and the purpose is not a tautology.

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 the tool is permanent and aggregated but does not explicitly contrast with siblings like analyst_monthly_performance or analyst_daily_summary. Usage context is implied but no when-not-to-use or alternative 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?

No annotations are provided, so the description carries full burden. It discloses caching behavior ('served from cache', 'cached ~5min'), cost implications ('no per-request AI cost'), and excludes AI insight text, giving comprehensive behavioral transparency.

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

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

The description is mostly concise but repeats the aggregate mood mention twice. Overall, it is front-loaded with the key purpose and remains efficient 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?

For a tool with no parameters and no output schema, the description covers usage, caching, authentication, limitations, and return values adequately, making it fully complete for an AI 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?

Input schema has zero parameters and 100% schema coverage, earning a baseline of 4. The description adds value by explaining the output content (aggregate mood, top 5 tokens) 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?

Clearly states the tool returns aggregate market mood with score/label and top 5 tokens. Explicitly distinguishes from 'sentiment_history' for per-token time-series, providing a specific verb and resource differentiation.

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: no auth required, direct alternative usage for per-token data, and mentions subscription requirements for full AI insights, creating clear when-to-use and when-not-to-use context.

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

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

With no annotations, the description carries the full burden. It states data source (DefiLlama), caching frequency, positive/negative net change meaning, and lists covered coins. It does not mention rate limits or output format, but for a 0-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?

Description is front-loaded and contains only relevant information. Slightly wordy with repetition of 'current snapshot' and endpoint URLs, but no wasted sentences. Reasonably 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?

Given no output schema and no annotations, the description covers source, caching, alternative tools, and data interpretation. It could mention that the output is JSON, but for a simple tool with no parameters, it is mostly 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?

No parameters exist; schema coverage is 100%. Baseline 4 per guidelines. The description adds context about what data is returned beyond the schema, which 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 retrieves current stablecoin supply and 24h net flows for USDT, USDC, DAI, and others, and distinguishes itself from siblings by naming alternatives (stablecoin_history, stablecoin_monthly). The verb 'Get' is specific and matches the tool's function.

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

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

Explicitly tells when to use this tool ('current snapshot') and when to use alternatives (daily time-series, monthly trends). Also mentions caching interval (~30min). No ambiguity about context.

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

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

With no annotations provided, the description fully covers behavioral traits: it explains the data source (DefiLlama), caching (5min), omission of cold-start days, and the meaning of each returned field (totalFlow24h, totalNow, signal). 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 concise but could be tightened. It includes some redundancy (e.g., mentioning default twice) and the structure is adequate but not optimized for quick scanning.

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 explains key return fields (totalFlow24h, totalNow, signal) and data characteristics (daily, omitted cold-start days). It lacks explicit format of the response but is otherwise sufficient for a single-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?

Although schema description coverage is 100%, the description contradicts the schema by stating 'max 180' while schema says maximum is 90. This inconsistency reduces clarity. The description adds little beyond the schema, and the conflicting values harm parameter 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 verb 'Get' and the specific resource 'daily historical stablecoin supply changes'. It distinguishes itself from the sibling tool 'stablecoin_flows' by noting the latter is for the current snapshot, making the purpose unambiguous.

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

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

The description explicitly advises when to use 'stablecoin_flows' instead ('for the current snapshot'), providing clear guidance on choosing between tools. It also specifies the data window (up to 180 days) and default/max parameters.

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

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

With no annotations, the description fully discloses behavioral traits: data is aggregated from daily snapshots before purge, never deleted, cached for 5 minutes, rate-limited, and requires no authentication. This provides clear expectations for an AI 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 concise, well-structured, and front-loaded with the core purpose. Every sentence adds value, listing fields and usage constraints without redundancy.

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

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

Given zero parameters and no output schema, the description covers all necessary context: data source (daily snapshots), aggregation (monthly), permanence, field list, authentication, rate limits, and caching. It is fully sufficient for an agent to use this 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?

The input schema has zero parameters, so baseline is 4 per guidelines. The description adds no parameter info, 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?

Description clearly states the tool returns a permanent monthly archive of stablecoin flow data, one row per month, aggregated from daily snapshots. It explicitly mentions the verb 'Returns' and resource 'permanent monthly archive', and distinguishes from likely real-time or daily tools by emphasizing permanence and long-term macro context.

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 usage details like no authentication, 60 req/min rate limit, and 5-min cache. However, it does not explicitly guide when to use this tool versus siblings such as stablecoin_flows or stablecoin_history, limiting differentiation 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?

No annotations provided, so description carries full burden. It discloses caching (~30s), return fields (verdict, per-source health, age, error count, etc.), and that it's a public health check. This is sufficient behavioral context for a read-only status 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?

Three concise sentences: first states action, second lists returns, third gives usage context. No redundancy; 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?

Despite no output schema, description thoroughly covers returned data: overall verdict, per-source health with age in seconds, recent 24h error count, MCP tool count, OpenAPI path count. Also mentions caching. Complete for a simple health check 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?

Tool has zero parameters with 100% schema coverage, so description adds no parameter details. Baseline of 4 applies because the schema fully describes the inputs (none), and the description adds value elsewhere.

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 'Check live API & system health' with a specific verb and resource. It distinguishes from sibling tools that are data-specific because 'status' is the only health check tool among many data endpoints.

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 'Useful for AI agents and developers to verify the platform is live before making requests', providing clear when-to-use guidance. No exclusions or alternatives needed due to the tool's unique 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?

No annotations provided. Description adds 'Cached ~1hr' and 'Educational only — not tax advice,' but fails to disclose error handling, rate limits, or what happens for unsupported jurisdictions.

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, no wasted words. First sentence provides purpose and scope, second adds important caveats.

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 adequately explains what the tool returns (tax brackets by jurisdiction) and includes context on caching and educational 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?

No parameters exist in schema; description fully defines the tool's functionality by listing jurisdictions and stating that it returns tax rate brackets.

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 and resource: 'Get crypto capital-gains tax rate brackets by jurisdiction'. It lists supported jurisdictions and distinguishes from siblings, none of which relate to taxes.

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 usage as 'Reference crypto tax-rate brackets ... for the tax calculator' and includes a disclaimer 'Educational only — not tax advice.' Lacks explicit when-not or alternatives, but no competing tax tools exist 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?

No annotations provided, so description carries full burden. Discloses 5-min cache, mentions meta fields (cacheAgeSeconds, tokenCount), and merging process. Good transparency beyond basic operation.

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

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

Two sentences, front-loaded with main purpose, no fluff. Each 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 no parameters and no output schema, description covers purpose, sources, caching, and metadata fields completely.

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, baseline 4. Description adds value by explaining output structure (meta fields) even though no parameter details needed.

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

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

Description clearly states 'Get currently trending crypto tokens' with specific sources (DexScreener + CoinGecko) and ranking by 24h volume. Differentiates from sibling tools like 'market_heatmap' or 'narratives'.

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

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

Implies usage for trending tokens but no explicit when-to-use or when-not-to-use compared to siblings like 'analysts_top' or 'market_heatmap'.

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: returns aggregated counts, no USD volume, served from cache with ~5min refresh, and limitations on data. No contradiction 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?

Description is concise yet comprehensive, covering purpose, differentiation, limitations, parameter usage, and caching. The single paragraph is well-organized with front-loaded key points. Minor room for improvement (e.g., bullet points) but strong overall.

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 low complexity (1 param, no output schema), the description fully covers all necessary aspects: what it returns, what it doesn't, how to use the parameter, and data source. 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?

Schema covers 100% of parameters with description. The tool description adds extra semantics: clamping behavior for window values outside range. This goes beyond the schema, justifying a score above baseline 3.

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 aggregated whale movement counts by chain and direction over 1-30 days. Distinguishes from sibling whale_movements by specifying it provides counts, not individual transfers. The verb 'Get' and resource 'whale activity' are specific and 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?

Explicitly directs users to use whale_movements for individual records with amounts. Provides context on what is not available (per-transaction detail, wallet addresses, USD volume). Also notes caching behavior, aiding in appropriate invocation.

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; description covers data freshness, caching, and retention. However, contradicts input schema: description says max 180 days, schema says maximum 90. This inconsistency undermines transparency.

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

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

Description is well-structured and front-loaded with purpose. Some redundancy (e.g., repeating default and max), but overall 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?

Explains return fields, data freshness (upsert every 5 min), retention (365 days), and caching. Missing output schema, but described adequately. Contradiction reduces completeness slightly.

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 description adds meaning (look-back window, default, limits). But the documented max (180) conflicts with schema (90), reducing reliability.

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

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

Clearly states it retrieves daily aggregated whale movement counts per chain, for trend analysis not individual transfers. Distinguishes from sibling tools like whale_movements that likely focus on individual records.

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 use for trend analysis, not individual transfers. Provides example questions. Does not explicitly mention alternatives, but the scope 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?

Discloses important traits: permanent (never deleted), grows indefinitely, 60 req/min limit, 5-min cache, no authentication, and exclusion rule. No annotations provided, so description carries full burden and does it 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?

Four well-organized sentences, front-loaded with main purpose, no redundancy or fluff. 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?

Despite no output schema or annotations, description covers data returned, constraints, use case, rate limits, and data source. Completely adequate for zero-parameter 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?

No parameters in schema; description adds meaning by listing the fields returned: totalMoves, totalUsdValue, inflowCount/outflowCount, daysInMonth, avgMovesPerDay. Baseline for 0 params is 4, description exceeds 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?

Clearly states it returns the permanent monthly archive of whale movement activity, aggregated from daily summaries. Distinguishes from siblings like whale_daily_summary by emphasizing permanence and historical 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?

Explicitly mentions use case for answering historical questions and provides exclusion criteria (months with <20 daily records). Could be improved by explicitly stating when not to use (e.g., for real-time data).

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 covers key behaviors: no auth required, public endpoint, paginated, 1-year limit, omission of explorerUrl, and lists supported chains and directions. This fully informs the agent of what to expect.

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-structured: starts with overall purpose, then details supported values, then examples. It is fairly long but every sentence adds value; slight redundancy in listing chain values again after schema.

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

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

The description lacks explicit response format details (e.g., pagination metadata, specific fields returned) despite having no output schema. It mentions omission of explorerUrl but does not define what is included. For a tool with 5 parameters, this is a notable gap.

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

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

All 5 parameters have schema descriptions (100% coverage), so baseline is 3. The description adds value by providing example queries (q=USDT, q=ETH+Whale+%237) and clarifying that period 365d retrieves up to 1 year of history, which goes 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?

The description clearly states the tool returns a paginated archive of whale on-chain movements with a 1-year limit. It specifies the verb 'returns' and resource, and distinguishes from siblings like 'recent_whales' by noting it's the public, unauthenticated counterpart.

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 analyse historical on-chain flow direction... without any credentials' and mentions it's the public counterpart to the authenticated endpoint (implying when not to use). However, it does not explicitly name sibling tools as 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, description fully discloses no authentication, rate limit (60 req/min), handling of unresolved USD with unresolvedUsdCount, and response structure. No contradictions or missing 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?

Description is thorough but slightly verbose. However, it is well-structured with front-loaded purpose, then details. Every sentence adds unique value (auth, rate, defaults, field explanations), so it earns its length.

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

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

Given no output schema, description fully covers response fields and their meanings. It also addresses auth, rate limits, and distinguishes from sibling tools. For a single-parameter tool, this provides complete context for an AI 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 already describes the period parameter with enum and default (100% coverage). Description adds value by explaining why the default is 7d (shorter than raw archive's 90d) and that rollup is most useful over a recent window, going 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?

Description clearly states it returns an aggregated statistics rollup of whale on-chain movements, distinguishing itself from the raw whale_movements tool by avoiding paging. It specifies breakdowns by chain and direction, making purpose specific and differentiated 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?

Explicitly says it's for AI agents to avoid paging through raw rows, and explains period defaults. Does not explicitly state when not to use, but implies use when aggregated totals are needed. The context of sibling tools provides implicit 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 the full burden of behavioral disclosure. It reveals that only wallets with ≥5 resolved signals receive a score (honest, never fabricated), that data is DB-backed with a 5-min cache, and retention details (365d, permanent monthly archive). This provides significant context beyond the basic function.

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 main purpose, then elaborates on data format, filtering, and backend details. It is relatively concise given the amount of information conveyed, though it could be slightly more streamlined. Every sentence provides useful 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?

Despite having no output schema, the description explicitly details the return format: 'One row per wallet per day: wallet address, chain, label, composite score (0-100), win rate, average return %, and sample count.' It also covers filtering, data source (whale_score_daily table), and retention. With only 2 simple parameters, this description is fully adequate 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?

Input schema coverage is 100% with descriptions for both parameters. The description adds context beyond schema: days default 30, max 90, chain optional, and the note about only wallets with ≥5 signals receive a score (which relates to the data returned). This adds meaningful value.

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 gets daily whale score history, ranking wallets by composite score over up to 90 days. It specifies the resource (whale scores) and verb (get history). While it doesn't explicitly contrast with sibling whale tools, the specificity of 'daily historical composite scores for tracked whale wallets' distinguishes its purpose well.

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 'useful for tracking smart-money wallet performance trends' and explains how to filter by chain. However, it does not provide explicit guidance on when to use this tool versus alternatives (e.g., whale_activity, whale_daily_summary) or when not to use it. Usage is implied but not contrasted.

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