tachyo

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently reveals that the free version returns a connect-CTA and that a grounded answer requires either a session_token from verify_wallet_ownership or an x402 payment proof. This adds meaningful context beyond the schema about authentication and monetization. However, terms like 'connect-CTA' and 'x402' are not fully explained, and the description does not cover error behavior or rate limits, so it falls short of a 5.

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

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

The description is concise, with the main purpose front-loaded in the first sentence. The additional details about language, free/payment tiers, and authentication are packed into a single terse line. It is efficient with no filler, but the phrasing is somewhat cryptic and lacks a clear structure (e.g., bullet points or distinct sections), making it slightly less readable than ideal.

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

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

Given the tool has 4 parameters, no output schema, and no annotations, the description should provide a fuller picture. It covers the primary purpose and the authentication gate, but it does not describe the return format or structure of the 'grounded answer,' nor does it explain edge cases like invalid session tokens or payment failures. For a natural language QA tool with monetization, this leaves notable gaps in the user's understanding of what to expect.

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

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

Schema description coverage is 0%, so the description must compensate. It does add value by explaining 'lang: en / pl' (valid values for the lang parameter), 'session_token (from verify_wallet_ownership)' (source and purpose of the token), and 'x402 payment proof' (format context for the payment parameter). The 'question' parameter is self-explanatory from its name and the tool's purpose. This goes beyond the bare schema, though it omits explicit syntax or format for the payment proof, preventing a 5.

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

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

The description clearly states the tool's function: 'Ask any market question in natural language and get a grounded answer.' This specific verb+resource ('ask market question') distinguishes it from sibling tools that retrieve specific metrics (e.g., get_buzz_score, get_trending). The phrase 'any market question' establishes it as a general-purpose QA tool, clearly differentiating it from the more focused sibling tools.

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

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

The description implies usage context by saying 'any market question' and explaining that the free tier returns a connect-CTA while unlocking a grounded answer requires a session_token or payment. However, it does not explicitly state when to use this tool versus the specialized get_* or find_* siblings, nor does it provide exclusions or alternative names. The guidance is helpful for the authentication process but lacks explicit decision-making support.

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

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

With no annotations, the description carries the full burden. It discloses output categories, access tiers, timeframes, universe constraints, and a disclaimer. This is solid transparency for a read-oriented data tool, though it does not detail exact return structure or edge cases.

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 and efficient, using em-dashes and semicolons to pack information into a compact paragraph. Every clause contributes value, though a brief bulleted list could improve 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?

For a tool with no output schema, the description is quite complete: it defines the two outcome types, access tiers, resolutions, universe, and disclaimer. An agent can reasonably select and invoke the tool, though exact output formatting remains unspecified.

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

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

Schema coverage is 0%, and the description only implicitly addresses the 'payment' parameter via the free/premium distinction. It does not explain 'session_token' or any other parameter behaviors. The description partially compensates for the lack of schema detail but leaves parameter semantics incomplete.

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

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

The description clearly defines the tool's purpose: identifying coins where attention and price diverge ('coiled' and 'quiet_mover'). It distinguishes from sibling tools by focusing on the fusion of attention and price, though it does not explicitly name alternative 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?

It provides contextual usage guidance: free vs. premium output, daily and 1-hour resolutions, crypto-only universe, and the requirement that tickers have both attention and price. It does not explicitly exclude other tools or compare with alternatives, but the context is sufficient for most use cases.

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

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

No annotations exist, so description carries full burden. It discloses survival gating, non-death-spiral filter, unvalidated nature of 'coiled' block, win-rate tilt not guaranteed, flat median outcome, and non-financial-advice disclaimer. This is rich behavioral context beyond typical descriptions.

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 but every sentence contributes meaning: strategy definition, gating, exclusivity, tier outputs, and risk caveat. Slightly verbose with 'Not financial advice' but overall efficient and front-loaded with the core definition.

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 annotations, zero schema coverage, and no output schema, the description does a decent job explaining the tool's purpose, strategy, limitations, and tiered outputs. However, it completely omits parameter guidance, leaving payment/session_token usage ambiguous. Not fully complete for 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 0% and description does not mention any of the three parameters (payment, window_days, session_token). Free/premium tier mention is disconnected from the payment parameter, and window_days/session_token are completely unexplained. Description adds no value for 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?

Description clearly specifies the tool's function: finding long candidates via mean-reversion from oversold/beaten-down names with volume survival gating. It distinguishes from siblings by explicitly excluding public catalysts/listings and positioning as the only long-side edge. The verb and resource 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 strong context: states this is the long-side mean-reversion read, explains exclusions (public catalysts priced in), and differentiates free vs premium outputs. Does not explicitly mention when NOT to use it vs alternatives, but the exclusions and 'one edge' framing imply use cases.

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 and handles it well. It discloses the data source (daily candles + digest), the disclaimer ('not advice, not intraday'), the components of each setup (pump %, strength vs BTC, weakness score, etc.), and the free/paid behavior (teaser vs. full list). It could go further by detailing response format or rate limits, but the disclosed context is substantial.

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 single paragraph is information-dense and well-organized: it starts with the core action, explains intents, lists output fields, and closes with access and disclaimers. Every sentence earns its place; there is no filler or repetition. The front-loaded action verb makes the purpose immediately clear.

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 (two intents, free/paid modes, custom signals) and the lack of an output schema, the description covers most essentials: what the setups include, the data origin, the non-advice disclaimer, and access requirements. It does not specify result limits or ordering criteria, but overall it provides a solid operational picture for an agent.

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

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

The schema has 0% description coverage, so the description must compensate. It explains the 'intent' parameter with its two options and their meaning, and clarifies that 'session_token' (from verify_wallet_ownership) and 'payment' (x402 proof) are access-unlock parameters. This adds meaningful context beyond the bare defaults in the schema, though it doesn't specify exact formatting for the payment 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 opens with a clear verb+resource: 'Screen for trade setups', then specifies the unique value proposition ('ranked from OUR computed signals (no hallucinated ranking)') and enumerates the intents (fade/momentum) with concrete definitions. This distinguishes it from sibling market tools like find_longs/find_shorts by focusing on computed signals and specific setup types.

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

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

The description gives explicit guidance on when to use each intent ('fade' for weak coins that pumped, 'momentum' for coins holding strength) and explains the access modes (free teaser vs. paid unlock via session_token or x402 payment). However, it does not explicitly mention exclusions or direct comparisons to sibling tools like find_longs/show_finds, so it lacks an explicit alternatives statement.

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 transparency burden. It discloses output structure (free vs premium, catalyst types, dated-unlock flag), quantitative details (count, top 3 tickers), and risk warnings (liquidity, borrow, squeeze, not financial advice). It does not mention rate limits, auth, or exact response format, but provides meaningful 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 a single, front-loaded paragraph with a clear topic sentence. It packs useful details efficiently, though it includes a 'not financial advice' disclaimer that adds length. Overall, it is concise and well-structured for the information conveyed.

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

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

The tool has no output schema or annotations, so the description must cover return details and usage context. It explains free vs premium outputs and catalyst types, but omits parameter effects (window_days, payment, session_token) and does not fully describe the response format. This leaves the description incomplete for a tool with three parameters and no structured output schema.

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

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

Schema description coverage is 0%, so the description must explain parameters. It mentions free vs premium, hinting at 'payment' role, but does not explain 'window_days' (default 30) or 'session_token'. The description fails to specify how these parameters affect the output or behavior, leaving a significant gap in parameter semantics.

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

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

The description clearly states the tool identifies 'Short candidates — coins with a BEARISH catalyst', which is a specific verb+resource. It also distinguishes itself from sibling tools by noting it captures 'the real short signal, which the momentum-based setups miss', contrasting with find_setups and find_longs.

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

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

The description implies when to use: when seeking short opportunities based on fundamental catalysts rather than momentum. It contrasts with momentum-based setups and mentions free vs premium access, giving context on tiers. It does not explicitly name alternatives or provide exclusions, but the sibling names and contrast are 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?

With no annotations, the description carries the full burden. It discloses the data basis (mention velocity, 24h vs 7d), the independence from platform APIs, access tiers (free vs premium), data sparsity effects ('Sparse data → coarse'), and a disclaimer ('Not advice'). This provides meaningful behavioral context beyond basic read-only implications.

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 compact three sentences that front-load the core purpose and then efficiently covers limitations, access tiers, and data dependence. Every sentence adds value with no redundancy or filler.

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

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

The description provides a good high-level understanding of the tool's function and limitations, but it omits essential invocation details: the exact payment syntax for free vs premium, the role of session_token, and the output structure. Given the lack of an output schema and 0% parameter documentation, the description should be more complete to enable correct tool use.

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

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

Schema description coverage is 0%, so the description must explain parameters. It explains the effect of 'payment' (free vs premium) but does not specify expected values or format. 'session_token' is completely unaddressed, leaving a critical gap for correct invocation. The description adds some semantic value but falls short of compensating for the lack of schema documentation.

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 identifies heating/cooling attention shifts using source-independent mention velocity with a 24h vs 7d baseline. It differentiates from siblings by explicitly noting the signal is not platform-specific, which distinguishes it from related tools like get_trending and get_buzz_score.

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

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

The description implies usage through the source-independence claim and free/premium tier breakdown, but it never explicitly states when to use this tool over alternatives or names any sibling tool as a suggested substitute. The guidance is contextual rather than comparative.

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

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

With no annotations, the description carries the burden. It adds helpful context: free vs premium data tiers (affecting output), daily resolution, and a clear note that it's relative-strength rotation, not market-cap dominance. It doesn't state rate limits or explicitly say it's read-only, but the 'get' verb implies a safe query.

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

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

The description is extremely concise, front-loaded with the core question, and every clause adds necessary information (method, resolution, tier differences, definitional clarification). No filler or repetition.

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

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

For a simple read tool with two optional parameters and no output schema, the description covers purpose, methodology, tier restrictions, and resolution. The only gaps are the unexplained session_token and lack of explicit output format, but the free/premium breakdown implies the return structure sufficiently.

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

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

The description gives meaning to the 'payment' parameter by explaining free vs premium outputs, which is useful given 0% schema coverage. However, 'session_token' is left completely unexplained, leaving a gap in 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 immediately states the tool's purpose with a clear question, specifies the exact metric (7d relative strength vs BTC), and explicitly disambiguates from market-cap dominance. This makes it distinct from sibling tools like get_market_breadth or get_market_regime.

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 use case is implied: if you want to know whether money is rotating into alts or BTC, use this tool. However, it does not explicitly name alternatives or provide when-not-to-use guidance, so the agent must infer selection among sibling tools.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It explains the scoring composition, the volume-weighting logic, and the free/premium access tiers. It does not mention authentication or output format details for the free tier, but it provides meaningful behavioral insights beyond a simple getter.

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 efficient, delivering purpose and caveats in three short segments. The free/premium pricing detail could be considered ancillary, but it remains concise and front-loaded with the core 'buzzing tokens' idea.

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?

Without an output schema, the description should clarify return values; it does state that premium provides 'the full ranking with scores + components', but the free tier is only described as 'top 3 igniting' with no detail on response structure. It also omits parameter value specifics and error behavior, so it is not fully complete for a tool with two unannotated 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 schema has zero description coverage for the two parameters, so the description must compensate. It implies that `payment` controls free vs premium access, but it does not explain the valid values or the role of `session_token`. This leaves a key parameter completely unexplained, providing only partial compensation.

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

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

The description clearly identifies the tool as returning a composite attention/buzz score for currently buzzed tokens, specifying the input components (crowd mentions + desk coverage) and the volume-weighted methodology. It also distinguishes itself from a bullish signal, giving it a unique scope among 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?

It provides clear context for when to use the tool (identifying tokens gaining attention) and explicitly warns that it is not a bullish signal, which serves as a 'when not to use'. However, it does not name alternative tools for price polarity or other signals, so it lacks explicit 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?

Without annotations, the description adds context: it states the computation basis (digest_selections vs mentions), explains output tiers (free vs premium), and includes a 'not financial advice' disclaimer. It doesn't disclose auth requirements or side effects, but for a read-only info tool this is reasonable.

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

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

The description is compact, with definitions and a caveat. The 'nobody else can compute' phrase is marketing fluff but not harmful. Generally 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, the description explains the core metric, defines the two possible directions, and specifies output scope by tier. It lacks explicit session/payment parameter guidance but is largely self-contained.

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

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

Schema has two params with zero description coverage, and the description doesn't mention them by name. However, it indirectly explains the 'payment' parameter's effect via free vs premium output tiers, partially compensating. 'session_token' remains unexplained.

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 explains the tool measures the gap between editorial coverage and crowd chatter, defining desk_ahead and crowd_ahead. It distinguishes from siblings by its unique cadence comparison, though it lacks a direct 'returns' verb.

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

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

It implies usage for assessing coverage vs crowd sentiment, and explicitly warns it's NOT a buy signal. However, it doesn't name alternative tools or specify when to use this instead of others.

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 responsibility for behavioral disclosure. It transparently reveals the paid/locked nature, the two ways to unlock content, and the output structure (actionable calls with contract addresses). It does not mention rate limits or error responses, but the core behavior is well 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 compact (approximately 70 words) and front-loaded with the core purpose, followed by parameter semantics and unlock instructions. Every sentence adds useful information without repetition 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?

For a tool with 7 parameters, no required fields, and no output schema, the description covers the main parameters and return behavior. It explains the premium/locked behavior and how to unlock. It omits the 'lang' parameter and does not fully detail the 'payment_required descriptor', but the description is sufficiently complete for an agent to invoke the tool correctly.

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

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

Schema description coverage is 0%, and the description compensates by explaining the meaning and allowed values for section (HOT/SIGNALS/WARNINGS/all), asset_class, ticker, timeframe, session_token, and payment. It also explains the relationship between session_token and verify_wallet_ownership. The only parameter not described is 'lang', but its default 'en' is provided in 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 identifies the resource as 'The paid Degen Digest' and its content ('actionable calls with contract addresses, grouped by section'). It distinguishes from sibling market tools by focusing on this digest and its premium nature. However, it lacks an explicit verb like 'retrieves' or 'returns', relying on the tool name to convey the action.

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

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

The description provides clear context on when to use the tool for the Degen Digest and explains the unlock mechanisms (session_token or x402 payment). It indicates that free access returns a locked teaser, which is an important prerequisite. However, it does not explicitly contrast this tool with sibling tools or specify when not to use it.

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

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

With no annotations, the description carries full responsibility, and it excels by disclosing the data's nature (a daily-USD-volume proxy), output buckets (deep/ok/thin/micro/unknown), the squeeze-risk flag, and the distinction between free and premium access. It also explains how to authenticate for premium data (session_token from verify_wallet_ownership or an x402 payment proof) and includes 'Not advice' as a disclaimer. No contradictions with structured data.

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 but information-dense, covering purpose, methodology, output categories, access tiers, authentication, edge cases, and a disclaimer in just four sentences. Every sentence adds value, and the structure flows logically from question to proxy to buckets to access tiers to 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 the tool's moderate complexity and lack of an output schema, the description provides enough context for an agent to understand what the tool returns: a bucket category, a squeeze-risk flag, and potentially an exact volume figure for premium users. It also addresses the 'unknown' edge case and notes the watchlist dependency. This is complete for the likely use cases.

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

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

Schema coverage is 0%, so the description must compensate. It explains that ticker refers to a token, session_token comes from verify_wallet_ownership, and payment is an x402 proof, thereby adding meaning beyond the bare schema. It doesn't detail the exact format of payment or the expected ticker format, but the provided guidance is sufficient for a user to understand the parameters' roles.

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

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

The description opens with a direct question 'How liquid is a token — can you size into it without moving the price?' which clearly establishes the tool's purpose as a liquidity assessment. It specifies the resource (token) and the core output (liquidity bucket), distinguishing it from sibling tools that focus on buzz, attention, or other metrics.

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

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

The description provides clear context on when to use the tool (when checking token liquidity) and explains the free vs. premium tiers, including how to unlock the exact volume via session_token or payment. It also notes that 'unknown' means the token is off the watchlist, which implicitly tells the user when the tool may not provide useful data. However, it does not explicitly mention alternatives among sibling tools.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It does disclose the free vs. premium data difference and the scope limitation ('breadth of OUR tracked set'), which adds valuable context. However, it omits any explicit statement about read-only nature, authentication requirements, or potential errors, and does not describe the output format or pagination.

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 reasonably concise and front-loaded with a purpose-defining question. It includes necessary information about free vs. premium and scope, but the closing 'Not financial advice' disclaimer and the rhetorical question add slight verbosity without contributing to tool invocation. Overall, it is well-structured but not maximally tight.

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 gives a clear conceptual overview and differentiates free/premium offerings, but it lacks details about the output structure, the purpose of session_token, and any prerequisites or error conditions. Without an output schema and annotations, these omissions make the tool less complete than it could be for an agent to use confidently.

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

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

The schema has 0% description coverage, so the description must compensate. It partially explains the 'payment' parameter through the free/premium distinction, but the 'session_token' parameter is never mentioned or explained. This leaves a significant gap in understanding how to invoke the tool correctly.

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 provides 'market breadth over our tracked crypto set' and distinguishes between free (advance/decline) and premium (intraday pulse and relative-strength) tiers. The opening question 'Real move or just the majors?' frames the intent, and the explicit scope note ('not the whole market') differentiates it from other market-wide tools like get_market_summary.

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

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

The description implies a clear use case: when you want to know if a market move is broad or concentrated in major coins. It provides context about comparing broad market participation, but it does not explicitly mention when not to use the tool or name alternative tools for similar queries, leaving some ambiguity for agent selection.

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

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

With no annotations, the description carries the full burden. It openly discloses the free/premium distinction, the best-effort nature of BTC trend with null fallback when the feed is unreachable, and that it is 'not advice.' These details provide meaningful behavioral transparency for a read-only tool, though it omits details like rate limits or authentication specifics.

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 a compelling question, then efficiently explains the output type, the free/premium distinction, and the reliability caveat. Every sentence adds unique information, and the structure is compact and easy to scan.

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

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

Given that there is no output schema, the description partially explains the return value (label vs. driver details) but does not describe the full response structure. It also leaves the two parameters unexplained, creating a significant gap for an agent trying to invoke the tool correctly. The core behavior is covered, but the parameter omission limits 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 has two parameters (payment, session_token) with no descriptions (0% coverage). The description mentions 'Free = the label; premium = every driver,' which hints at payment but never explains how to set the payment parameter or what session_token is for. It fails to compensate adequately for the missing schema descriptions.

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

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

The description clearly states the tool's purpose by posing the question 'Is the market risk-on or risk-off right now?' and specifying the output categories (BULLISH/BEARISH/CHOPPY) derived from a breadth + relative-strength composite. It explicitly distinguishes itself from a forecast and other sibling tools that provide different market analytics.

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

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

The description gives clear context on when to use the tool—when you need the current market regime—and clearly states what it is not (a forecast). However, it does not explicitly name alternative tools or provide direct when-not-to-use scenarios, so it stops short of a 5.

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

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

With no annotations, the description carries the full burden. It discloses critical behavioral traits: timeframe clamping by tier, free vs paid access, and the exact auth mechanisms (session_token from verify_wallet_ownership or x402 payment proof). This goes beyond minimal and gives the agent a comprehensive understanding of constraints and requirements.

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 and information-dense, using a compact bullet-like structure. Every sentence earns its place: the first line states the core purpose, the second details all filters and tier behavior, and the third explains access levels. No filler or redundant content.

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

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

For a tool with 5 optional parameters and no output schema, the description covers all necessary selection and invocation aspects: what the tool does, filter options, tier constraints, and access requirements. It is complete enough for an agent to decide when and how to call it correctly.

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

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

Schema description coverage is 0%, so the description is the sole source for parameter meaning. It explicitly enumerates valid values for timeframe, category, and lang, and clarifies the purpose of session_token and payment. This fully compensates for the lack of schema descriptions and provides actionable guidance.

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

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

The description states a specific verb and resource: 'Market recap — filterable by timeframe and category.' This clearly differentiates it from sibling tools like get_market_breadth or get_trending, which target different metrics. The title also includes the market summary scope, making the tool's purpose unmistakable.

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 on when to use the tool: for a market recap with timeframe and category filters. It also explains tier-based limitations (free≤24h, connected≤7d) and how to unlock the full recap via session_token or payment. However, it does not explicitly mention alternatives or when not to use this tool, hence not 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?

With no annotations, the description carries the transparency burden. It usefully discloses that 'Energy = item count, NOT sector returns' and describes free vs premium output differences. However, it does not mention response format, pagination, authentication requirements, or rate limits, leaving significant behavioral aspects undisclosed.

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 tightly written in three sentences, front-loading the core purpose, then adding categorical scope, tier differences, and a definition of the key metric. No redundant words; even the 'Not financial advice' disclaimer is common boilerplate and does not detract from its efficiency.

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

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

The tool has no output schema and no annotations, so the description needs to explain what the user should expect. It provides a useful conceptual model (grid categories, free/premium scope, energy meaning) but stops short of describing the actual return structure, example output, or parameter-specific behavior, leaving ambiguity for real 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 0%, so the description must compensate. It indirectly explains 'payment' through the free/premium distinction, but it does not explicitly state parameter values or validate the mapping. The 'session_token' parameter is completely unexplained, leaving a gap for a 2-parameter tool.

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

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

The description clearly states the tool provides a 'narrative-energy grid' across six named categories, answering where market conversation is concentrated. It distinguishes itself from siblings by focusing on sector-level heatmap rather than individual metrics like attention shifts or buzz score, though it lacks a direct verb like 'get'.

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

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

Usage context is implied through the question 'Where is the market conversation concentrated?' and the mention of free/premium tiers, but there is no explicit guidance on when to prefer this tool over siblings such as get_attention_shifts or get_market_breadth. No exclusionary or alternative suggestions are provided.

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

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

With no annotations, the description fully bears the transparency burden. It discloses that the feed is de-identified (no wallets, addresses, tags), describes what the free vs premium outputs contain, and warns that the signal is unvalidated and not financial advice. This is rich behavioral disclosure.

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

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

The description is information-dense but well-structured: it starts with the core purpose, then adds de-identification, parameter options, access tiers, and a caveat. It's a bit long but each sentence contributes meaningful detail, so it earns a 4 rather than a 5.

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

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

Given the lack of output schema and annotations, the description covers the essential aspects: what it does, parameters, access levels, output contents (free vs premium fields), and the unvalidated warning. It does not explain return format or error handling, but it is reasonably complete for a data-lookup tool.

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

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

Schema description coverage is 0%, so the description compensates by explaining window_hours with explicit valid values (6/12/24/48), and clarifying that session_token comes from verify_wallet_ownership and payment is an x402 proof. It covers all three parameters, though it doesn't give exact format specifications.

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

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

The description opens with a specific question 'Which tickers are smart-money / KOL wallets net-buying right now?' which clearly states the tool's function. It further defines the resource as a 'de-identified market-wide net-USD accumulation feed' and distinguishes it from sibling tools like get_whale_alerts by emphasizing no wallet/address/tag 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: it explains the free vs premium tiers and how to unlock full data via session_token or x402 payment, and adds a caveat that the signal is unvalidated. However, it does not explicitly mention alternative tools or when not to use this one, so it stops short of a 5.

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

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

Since no annotations are provided, the description carries the full burden. It discloses free vs. unlocked tiers, the requirement for session_token or payment proof, and the meaning of 'No coverage'. This is significant behavioral context beyond basic functionality.

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

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

The core purpose is front-loaded in the first phrase. Each sentence adds value, and parameter explanations are inline and compact. No fluff or repetition.

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

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

Even without an output schema, the description conveys what the user gets: dossier features, free vs. full versions, and the no-coverage case. It doesn't detail the exact return structure but gives enough for an agent to understand the tool's output and access requirements.

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

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

Schema description coverage is 0%, so the description compensates by explaining ticker with an example, window_days range, session_token source, and payment as an x402 proof. The 'lang' parameter is omitted, but it is a simple optional string with a default.

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 retrieves a per-ticker digest narrative over a window, listing specific content (section appearances, notes, price path). It distinguishes itself from on-chain scoring tools by emphasizing 'OUR narrative on the token'.

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

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

Provides context on when to use (when you need our narrative on a specific token) and explicitly excludes on-chain scoring, hinting at when not to use it. However, it does not name specific alternative sibling tools or give explicit 'use instead' 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 the full burden. It adds valuable behavioral context: '1h is the freshest but coarsest read (flagged if possibly-missing)', 'horizons differ in resolution', and the meaning of 'No coverage'. This goes beyond a simple function statement and informs the agent about data caveats.

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

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

The description is somewhat long but front-loaded with the primary purpose. Each sentence adds value, including pricing tiers, data freshness caveats, and coverage status. It could be tightened, but it remains organized and efficient.

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

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

With no output schema, the description explains return value components (momentum horizons, relative strength, alignment verdict) and covers edge cases like 'No coverage'. However, it omits details about payment/session_token usage and any potential error conditions, leaving some context gaps for a 3-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?

Schema description coverage is 0%, so the description must compensate for explaining parameters. It only indirectly references 'ticker' via 'one token' and does not explain 'payment' or 'session_token' at all, despite mentioning free vs premium which hints at payment semantics. This leaves key parameters underdocumented.

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

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

The description clearly states the tool's function: 'Multi-horizon momentum for one token' with specific horizons (1h, 1d, 7d) and relative strength vs BTC, plus an alignment verdict. This specific verb+resource structure distinguishes it from siblings like get_market_summary or get_ticker_dossier.

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 token-specific momentum analysis with 'one token' and the momentum horizons, but it does not explicitly state when to use this tool instead of alternatives or mention exclusions. No sibling comparisons or when-not-to-use guidance is given.

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

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

With no annotations provided, the description carries the behavioral disclosure burden. It clearly explains the free vs. full ranking behavior, including the unlock mechanism via session_token or payment proof, and mentions the timeframe options. This adds valuable context beyond the bare schema.

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

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

The description is three sentences, front-loaded with the core purpose, and each sentence adds necessary information: purpose, timeframe, and access tiers. No filler or 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 simple tool with no output schema, the description covers key aspects: what it returns (top 3 vs top 15 with counts), how to unlock full data, and available timeframes. It does not detail the exact output structure, but that is not strictly required given the description's clarity.

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

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

The schema has 0% parameter description coverage, but the description compensates well: timeframe is explained with allowed values (24h/7d/30d), payment is described as an x402 proof, and session_token is linked to verify_wallet_ownership. It does not specify exact formats, but provides enough to understand purpose and usage.

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 the tool's specific function: returning trending tokens (most-mentioned tickers). The verb+resource combination is clear, and it distinguishes itself from sibling tools like get_buzz_score or get_attention_shifts by focusing on mention frequency.

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

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

The description implies when to use the tool (when interested in trending tokens by mentions) and explains the timeframe options. However, it does not explicitly name alternative tools or state when not to use it, leaving some room for inference.

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

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

With no annotations provided, the description carries the transparency burden. It discloses the free vs. premium tier difference, the authentication methods (session_token from verify_wallet_ownership or x402 payment proof), and that the data is public. It does not mention rate limits or exact failure modes, but it adequately sets expectations for a read-only data query.

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 primary purpose and covers necessary details. The middle sentence is somewhat long and packs multiple ideas, but every sentence contributes meaningful information without excessive verbosity.

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

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

The description covers the tool's output content, free/premium behavior, authentication, and public data status. With no output schema, this is sufficient context for an agent to select and invoke the tool. Minor gaps exist, such as not detailing the exact response format or pagination, but these are not critical for this use case.

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 provides only parameter names and defaults with no descriptions (0% coverage). The description compensates fully by explaining ticker as an optional filter, and both session_token and payment as premium access mechanisms, even specifying where session_token comes from. This is excellent 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 identifies the tool's function: retrieving recent large on-chain whale moves, including tokens, USD size, and direction. It distinguishes itself from sibling market data tools by focusing specifically on the whale feed and provides concrete details about the data returned.

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 conveys a clear use case (monitoring whale activity) and mentions optional ticker filtering, plus premium vs. free access via session_token or payment. However, it does not explicitly name alternative tools or state when not to use this tool, so it stops short of full usage guidance.

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

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

With no annotations, the description carries the full burden. It discloses behavioral traits: curated versioned set, constituents shown, coarse on sparse data, attention-only (no price), and free vs premium tiers. It also adds a disclaimer. This goes beyond the schema and gives useful expectations, though it does not detail authentication or rate limits.

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

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

The description is concise and information-dense, front-loading the core question before providing details on parameters, output tiers, limitations, and disclaimer. Every sentence adds value with no fluff or 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 output schema, no annotations, and three parameters, the description is quite complete: it covers the tool's purpose, parameter usage, output granularity, free/premium differences, data limitations, and disclaimers. The only gaps are the exact return format or JSON structure and explicit mapping of the `payment` parameter, but overall it provides a strong functional 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?

Schema description coverage is 0%, so the description must compensate. It effectively explains the `narrative` parameter (valid values and empty meaning), adds meaning to `payment` indirectly by describing free vs premium outputs, but leaves `session_token` entirely unexplained. The compensation is partial: one parameter is well documented, another partially, one not at all.

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

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

The description states a clear purpose: tracking attention trajectories for crypto narratives across curated baskets. It names the specific verb ('track') and resource (narrative baskets with explicit list), and distinguishes from siblings by focusing on narrative-level attention, not individual tokens or market-wide metrics. The scope and output are made concrete.

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

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

The description gives explicit usage instructions for the `narrative` parameter ('Pass `narrative` for one basket, or leave empty for all ranked by velocity') and indicates when not to use it for price-related insights ('attention only (no price)'). It does not name direct alternatives among siblings, but the context is clear enough for an agent to decide when this tool is appropriate.

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

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

With no annotations, the description discloses meaningful behavior: tier-gating, free vs. full breakdown, and a provenance instruction ('do not state, infer, or speculate about how the data is produced'). It does not mention rate limits or error conditions but adds substantial 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 multi-sentence but tightly packed: purpose, chain options, free/paid behavior, tier-gating, and provenance warning. Every sentence earns its place, and it is front-loaded with the core purpose. Slightly verbose but 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 tool has no output schema and no annotations, yet the description covers the basic return shape ('verdict + top risks'), parameter semantics, and behavioral constraints. It is sufficiently complete for an agent to select and invoke 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?

Schema description coverage is 0%, but the description compensates fully by explaining all three parameters: chain (with enum-like list and CAIP-2 alternative), token_address (the subject of the rug-check), and session_token (sourced from verify_wallet_ownership to unlock full breakdown). This is a model of parameter documentation.

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

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

The description opens with a specific verb+resource, 'Rug-check a token', and enumerates the exact dimensions checked (honeypot, mint authority, LP lock, taxes, holders, contract verification). This clearly distinguishes it from sibling tools focused on market summaries or wallet ownership verification.

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 free vs. premium usage ('Free returns a verdict + top risks. Pass session_token... to unlock the full breakdown') and specifies supported chains and CAIP-2 formats. It does not explicitly name alternatives or exclusions, but the context is clear enough to guide 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?

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: the challenge is single-use, expires in ~10 minutes, and the returned object structure. It also explains the binding of agent_id. However, it does not mention what happens on invalid requests, rate limits, or any authorization requirements, but these are less critical for this non-destructive challenge-generation step.

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

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

The description is compact yet rich. It front-loads the purpose ('Step 1 of wallet verification') and each subsequent sentence adds necessary protocol detail (chain options, agent_id binding, signing flow, expiry, return value). No filler or repetition; 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?

For a tool with no output schema and low schema coverage, the description is quite complete. It explains the return shape, the follow-up action, and the single-use/expiry behavior. Missing are the meaning of the 'address' parameter and any error/edge-case handling, but the essential invocation context is present.

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

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

Schema description coverage is 0%, so the description must compensate for all parameters. It explains the 'chain' values and the purpose of 'agent_id', but the required 'address' parameter is never described. An agent might infer it is the wallet address to verify, but that is not explicitly stated. This gap in a required parameter is significant.

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

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

The description clearly states the tool's purpose: 'Step 1 of wallet verification: get a fresh challenge for the user to sign.' This is a specific verb+resource action, and it distinguishes itself from the sibling tool verify_wallet_ownership by explicitly labeling it as step 1 and describing the follow-up call.

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: it explains the workflow step-by-step, tells the agent to present the challenge to the user, and instructs to call verify_wallet_ownership with the returned nonce and signature. It also specifies allowed values for chain. This clearly differentiates when to use this tool versus the verification sibling.

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

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

With no annotations, the description carries the full burden and it delivers by stating 'Does not move funds or expose keys' and explaining the success flow (wallet linked, session_token, unlock tiers). It also reveals the return shape. It does not mention failure modes or rate limits, but for a verification step the disclosed side effects are sufficient.

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

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

The description is concise yet rich, fitting essential workflow details, parameter semantics, return fields, and safety guarantees into a few lines. It is front-loaded with the step context, and every 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 output schema or annotations, the description provides a thorough overview: prerequisites, parameter semantics, expected output, and safety. It lacks explicit error handling or failure scenarios, but for a 5-parameter verification tool, the description is quite complete and leaves no major gaps.

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

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

Schema coverage is 0%, so the description must compensate. It does by explaining chain values ('evm' vs 'solana'), the signature format for each, that nonce comes from request_verification_challenge, that the signature must be over that exact challenge text, and that agent_id must be the same as the challenge request. Address is self-explanatory from context, so all parameters gain semantic meaning beyond the bare 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 is 'Step 2 of wallet verification: prove control by signing the challenge from step 1.' This gives a specific verb ('sign') and resource ('challenge') and distinguishes it from the sibling tool request_verification_challenge, which is step 1. It also mentions the outcome (wallet linked, session_token) and explicitly states it does not move funds or expose keys.

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 frames the tool as 'Step 2' and references step 1 (request_verification_challenge), telling users to use the nonce from that challenge and pass the same agent_id. It also explains the downstream use of the session_token with other agents like check_token_safety. However, it does not explicitly state when NOT to use the tool or mention alternatives, which is less critical here given the sequential nature.

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