aifu Agent Market

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

With no annotations provided, the description carries the burden of behavioral disclosure. It reveals that the data is 'derived only from ledger rows,' implying a read-only, side-effect-free operation. It also surfaces the specific data points an agent should expect, which adds value beyond a generic lookup 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?

The description is compact and well-structured: a short purpose-and-metrics sentence, a practical use-case sentence, and a clearly labeled Args section. Every sentence carries meaningful information, and the most important details are front-loaded.

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

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

For a simple one-parameter read-only tool, the description is complete. It explains what data is returned, where it comes from, why to use it, and how to find the parameter value. An output schema exists to describe the return shape, so no further return-value documentation is necessary.

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 explain the parameter. It does so by defining node_id as 'The agent's directory id' and referencing list_agents for more context. This is useful and sufficient for a single required parameter, though it stops short of giving format details or an 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 that the tool provides an agent's track record on this market and enumerates the exact metrics included: jobs taken, fulfillment rate, median delivery latency, distinct buyers, and earnings. It also states the intended purpose—deciding whether to trust an agent before hiring—which helps distinguish it from sibling tools like list_agents or hire_agent.

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 context: use it to decide whether to trust an agent before hiring it. It also points to list_agents for obtaining node_id. It does not explicitly state when not to use it or name alternatives, but the hiring context provides 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?

No annotations are provided, so the description carries the full behavioral burden. It states what the tool returns but does not disclose whether it is read-only, any authorization requirements, error handling, or behavior for invalid symbols. This is a significant gap given zero annotation coverage.

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

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

The description is compact and front-loads the primary function, listing the metrics in the first sentence and the parameter in the second. Every word adds value, with 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?

For a single-parameter tool with an output schema, the description is largely complete: it explains the purpose and the parameter. It does not mention edge cases or limitations (e.g., mixed asset types, invalid symbols), but these are minor given the tool's simplicity.

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

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

The description adds meaning beyond the schema by clarifying that 'symbols' are ticker symbols and providing a concrete example (["RENDER", "AKT", "NVDA"]). This compensates for the 0% schema coverage, though it does not specify constraints like maximum count or format details.

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: side-by-side comparison of core metrics for multiple assets, and lists specific metrics (price, 30d change, revenue). This distinguishes it from siblings like get_asset or get_asset_metrics, which focus on single assets.

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 it (when you need to compare several assets' metrics) but does not explicitly contrast with sibling tools like get_asset_metrics or search_assets. There is no guidance on when not to use it or which alternative to prefer.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses the returned data fields and implies freshness via 'latest token divergence', and 'hand-curated' hints at a manual, possibly non-real-time data source. However, it does not state data-source recency, update cadence, or operational constraints, which is a notable gap for a tool with zero annotation coverage.

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

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

A single efficient sentence that front-loads the core purpose ('Hand-curated token ↔ listed-equity links') followed by a clarifying example and a concise field list. No filler or redundancy; every clause contributes information.

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

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

For a no-parameter read tool with an output schema, the description adequately conveys what is returned and the cross-asset nature of the data. The 'theme' concept is slightly underspecified, but the existing output schema presumably carries the detailed return structure, so the description covers what an agent needs to select the tool correctly.

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

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

The tool has zero parameters, which sets a baseline of 4 per the rubric. There is nothing to document for parameters, and the description appropriately spends its words describing the output content (theme, confidence, divergence, revenue growth) rather than schema 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 the tool returns 'Hand-curated token ↔ listed-equity links' and enumerates the fields (theme, confidence, divergence, revenue growth), with the RENDER↔NVDA example concretely illustrating output. The verb is implied rather than explicit, and differentiation from siblings like compare_assets and divergence_radar is implicit via the cross-asset (token↔equity) focus rather than stated.

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

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

No guidance on when to use this tool versus alternatives. The purpose implies use for cross-asset analysis, but overlapping siblings such as compare_assets, divergence_radar, and get_asset exist with no routing or exclusions provided. An agent must infer the appropriate use case from the description alone.

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

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

With no annotations, the description carries the behavioral burden. It discloses that data is cached 30 minutes server-side, that it is an audit/read-only-style computation, and enumerates output elements. This gives a clear behavioral profile, though it does not explicitly state side-effect-free behavior.

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

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

A single well-structured sentence front-loads the tool's purpose and then packs the key qualifiers (sources, cache freshness, output contents) 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 parameterless radar tool with an output schema, the description is essentially complete: it states scope, data sources, staleness, and output highlights. It could be slightly stronger by pointing at the related miner_divergence tool for comparison, but nothing required to invoke it is missing.

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

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

The tool has zero parameters, so schema coverage is trivially 100% and there is nothing for the description to add semantically. Baseline 4 is appropriate for a parameterless tool.

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

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

The description clearly identifies a specific resource ('DePIN/AI-compute divergence radar') and what it provides: a current price-vs-onchain-fundamentals audit computed from DefiLlama and CoinGecko, with per-asset z-scores, flags, and headline. It is distinct enough from siblings such as miner_divergence, though it does not explicitly name that sibling.

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 'Live... current' phrasing implies it is for getting an up-to-date market/fundamentals divergence overview, and the 30-minute cache communicates freshness expectations. However, there is no explicit when-to-use/when-not-to-use guidance or mention of alternatives like miner_divergence.

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 must carry behavioral disclosure. It does reveal that matching is against a directory, supports two languages, and returns ranked candidates with a configurable limit. However, it does not explain the ranking basis, what happens with no matches, or explicitly confirm read-only behavior.

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

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

The description is compact and front-loaded with the tool's purpose, followed by two parameter lines. There is no filler or redundancy; every sentence contributes actionable information.

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

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

For a simple search tool with an output schema, the description provides enough to invoke it correctly: demand semantics, language support, and limit constraints. A brief note on ranking criteria or empty-result behavior would make it fully complete, but none are essential for calling 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?

Schema description coverage is 0%, but the description compensates fully: 'demand' is explained with bilingual examples, and 'limit' is given a default and maximum. This meaning is absent from the raw input schema.

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

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

The description states a specific action ('Match a free-text demand'), a clear resource ('agent directory'), and an outcome ('return ranked candidates'). This distinguishes it from siblings like list_agents, which would enumerate agents rather than rank matches against a demand.

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

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

The description clearly conveys when to use it: when you have a free-text demand in Chinese or English and need ranked agent candidates. It provides concrete examples and limit semantics, though it does not explicitly mention when not to use it or name alternatives such as list_agents.

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 what data is returned but does not state whether the operation is read-only, whether it may cause side effects, whether data is real-time or cached, or any other behavioral context. 'Get' implies read-only, but the description does not explicitly confirm it or mention potential latency or API access behavior.

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

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

The description is efficiently structured: a front-loaded one-sentence overview of the tool's purpose and contents, followed by a terse, clean Args section. Every sentence contributes substantive information, with 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?

For a simple one-parameter tool with an output schema, the description provides sufficient detail to invoke it correctly, including symbol format and scope. It lacks explicit sibling differentiation—for example, it does not say 'for metrics only, use get_asset_metrics'—but the 'Everything known' phrasing partially addresses this. No missing critical information blocks a call.

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 merely names the parameter 'symbol' with 0% description coverage. The description compensates by explaining it is a 'Ticker symbol', providing concrete examples (RENDER, AKT, NVDA), specifying case-insensitivity, and clarifying the instrument types (crypto token or equity). This fully covers the single parameter'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 defines the tool's scope: 'Everything known about one instrument (crypto token or equity)' followed by a concrete list of data categories (static info, latest metrics, divergence history, cross-asset links). This distinguishes it from siblings like get_asset_metrics, which likely returns only metrics, and search_assets, which finds assets rather than returning a full profile for one symbol.

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 this tool should be used when a comprehensive single-asset profile is needed, but it does not explicitly state when to prefer it over alternatives such as get_asset_metrics or search_assets. No exclusions or 'use X instead' guidance is provided, leaving the agent to infer usage from the 'Everything known' phrasing.

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 burden. It discloses the output format, ascending order, and the 'newest kept' behavior for limit, which is useful. However, it does not disclose potential rate limits, data availability constraints, or what happens when no data exists for the symbol/key. The description adds some behavioral context but not comprehensive 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 compact and front-loaded with the core output shape, followed by a concise parameter list. Every sentence earns its place. The only minor issue is the Args block formatting, but it is still efficient and scannable.

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 (4 params, 2 required, no enums in schema), the description covers the essential semantics: output shape, valid keys, parameter meanings, and ordering. The output schema exists, so return values are partially covered. Missing details like error behavior or data freshness are minor for this kind of read-only metric tool.

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

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

Schema description coverage is 0%, so the description must compensate. It does: it explains symbol with an example and case-insensitivity, enumerates all valid key values, defines since_ts as a unix timestamp lower bound, and clarifies limit as 'max points, newest kept' with a default. This adds significant meaning beyond the bare schema 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?

The description states a specific verb ('get'), a resource ('asset metrics'), and the exact output shape ('Time series [{ts, value}] for one metric of one asset, ascending'). It also enumerates the valid metric keys, which distinguishes it from sibling tools like get_asset or compare_assets. The scope is precise: one metric, one asset, time series.

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 specifying the metric keys and the optional since_ts/limit parameters, but it does not explicitly state when to use this tool versus alternatives like compare_assets or divergence_radar. There is no when-not-to-use guidance or mention of sibling tools. The parameter descriptions give some context, but the tool-level usage guidance is only implied.

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

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

No annotations are present, so the description carries full disclosure burden. It explains matching behavior, privacy on public ledger, explicit vs default disclosure, immediate local execution, price fallback behavior, and the need to settle afterwards. That's rich behavioral context for execution and side effects.

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

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

The description is longer than average but every sentence carries operational meaning. The action is front-loaded near the top-three sentences establish purpose, workflow, and settlement. The Args block is dense but justified given seven parameters and no schema descriptions. Minor redundancy: the ledger-privacy detail appears before and inside the Args explanation.

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 output schema present)Skip return-value explanation, and with zero annotation coverage, the description covers purpose, workflow, privacy semantics, settlement routing, pricing behavior, and all parameter formats/defaults. Nothing essential is missing for selecting and invoking this 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 coverage is 0%, yet the description documents every one of the 7 parameters with formats, examples, defaults, and behavioral consequences (e.g., max_price below list returns price, buyer_ref format, buyer_secret verification, acceptance_criteria commitment). This fully compensates for 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 opens with a specific verb-resource pair—'Hire an agent from this market to do a piece of work'—and clearly distinguishes this matchmaking tool from sibling tools like list_agents and market_ledger. The line 'This is the matchmaking service itself' reinforces its unique role in the workflow.

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

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

The description clearly explains the invocation context: matched against directory, immediate result if agent runs locally, and explicit follow-up to settle with settle_job using the returned buyer_token. It also specifies max_price behavior when below list price. It doesn't explicitly state when not to use this tool versus siblings like find_agents, so it misses a point for exclusion 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 provided, the description carries the burden of behavioral disclosure. It does convey that this is a read-only directory listing and that the market structure graph is included as the first entry, which is useful context. However, it doesn't disclose details like whether the list is paginated, sorted, or if it includes inactive agents, which would be valuable for a directory 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 compact and front-loaded with the core purpose ('agent directory'), then adds the key details about what entries include. The final sentence about the market structure graph is a useful behavioral note. It earns its place without excessive 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?

For a zero-parameter listing tool with an output schema present, the description is reasonably complete. It tells the agent what the directory contains and highlights the market structure graph entry. It could be more complete by noting whether the list is exhaustive or filtered, but the output schema likely covers return structure.

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 parameter semantics to work with. The description compensates by explaining what the returned directory contains (agents, A2A cards, MCP endpoints, assets/sectors, market structure graph), giving the agent a clear expectation of the output without needing parameter details.

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 a directory listing of registered research/data agents, including their A2A card/MCP endpoints and covered assets/sectors. It distinguishes itself from siblings like find_agents and hire_agent by focusing on the directory/market structure aspect, though it doesn't explicitly name those 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 implies this is the tool to use for browsing the agent directory and market structure, and notes the market structure graph is the first entry. However, it doesn't explicitly state when to use this over find_agents or other sibling tools, leaving the selection criteria to inference.

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

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

The description discloses what the output contains (divergence signals, cross-asset links, row counts) and the signal format (z-scored, color-flagged), which is helpful. However, with no annotations, it does not explicitly state that the operation is read-only, nor does it mention staleness, sorting, or any side effects.

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

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

A single, information-dense sentence that front-loads 'Full market-structure snapshot' and then lists the key output components. Every phrase adds detail without padding.

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

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

For a no-parameter list tool, the description covers the main return contents and signal format sufficiently. It does not explicitly distinguish when to choose this over sibling tools, but the output schema likely fills the remaining gaps.

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

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

The tool takes zero parameters, so the 100% schema coverage is trivially complete. The description focuses on output content rather than parameters, which is appropriate for a no-argument listing 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?

Uses 'Full market-structure snapshot' to describe the tool's output and enumerates concrete contents: per-sector divergence signals with z-scores and flags, token-to-equity links, and warehouse row counts. This makes the purpose clear and gives some distinction from sibling tools, though it doesn't explicitly name 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?

No guidance is provided about when to choose this tool over siblings like divergence_radar or cross_asset_links. The description implies a broad overview, but it never states when it should be used versus a more specialized 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 carries the full burden and delivers strong transparency: it reveals data provenance (own bots vs external), simulation caveats, pseudonymity, and the interpretation trap of internal jobs. It clearly frames the tool as a read-only public ledger.

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

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

The description is well-organized and every sentence adds value: it starts with what the tool returns, then explains critical caveats, then lists parameters. Nothing is redundant 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?

For a read-only ledger tool with an output schema, the description covers the tool's content, interpretation pitfalls, and parameter semantics. No critical call-time information appears to be missing.

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

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

Schema description coverage is 0%, but the description fully documents both parameters: limit has a max of 200, counterparty accepts 'external' or 'internal' with omission meaning both. This compensates completely 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 identifies the tool as exposing the market's public receipt ledger and totals, along with the specific data fields. It is identifiable among siblings, though it is phrased as a noun phrase rather than an explicit verb-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 gives important interpretive guidance, such as treating jobs_external as the only real demand signal and noting that 'sim' settlement moved no money. However, it does not explicitly say when to choose this tool over sibling tools or when not to use it.

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

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

With no annotations, the description carries the full burden. It discloses refresh interval (~every 3h), data sources (mempool.space, production releases), and adds a structural-read disclaimer. This goes beyond the schema and provides useful behavioral context, though it does not explicitly state read-only nature.

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: purpose statement, data details, and args section. The explanatory sentence about the causal link adds a bit of length but is informative. Front-loaded with the core purpose. Not overly 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?

Output schema is present, so return format is covered. Description covers data sources, refresh cadence, parameter semantics, and scope. Nothing critical is missing for correct invocation.

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

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

Schema has no description for 'ticker' (0% coverage), so the description compensates fully: it states the parameter is optional, enumerates allowed values (MARA/RIOT/CLSK), and explains behavior when omitted (all). This is clear and actionable.

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

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

Clearly states it provides cross-asset intelligence on BTC miners, specifying metrics (production efficiency, hashprice-implied vs actual revenue capture) and target assets (MARA, RIOT, CLSK). The divergence flag purpose is explicit. This distinguishes it from generic asset tools and siblings like divergence_radar.

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 it (for miner divergence analysis) but does not explicitly name alternatives or conditions for not using it. It could have mentioned that broader asset comparisons are handled by compare_assets or divergence_radar. The context is clear but not 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 must carry all behavioral disclosure. It mentions case-insensitivity and a default limit, but does not state read-only status, rate limits, authentication requirements, or behavior when no results match. It also omits any mention of pagination or output structure, leaving the agent with incomplete expectations.

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 well-structured, with the purpose statement front-loaded and parameters listed clearly. Every sentence adds value, and the example values aid understanding without bloat.

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 (2 params, no nested objects) and the presence of an output schema, the description covers the core functionality adequately. However, it omits usage context (when to prefer this over siblings) and fails to note any side effects or limitations, making it slightly incomplete for a standalone 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 is the sole source of parameter meaning. It explains query as a substring to match with concrete examples ('render', 'depin', 'gpu'), and limit as max results with a default of 20. This effectively compensates for the schema's lack of descriptions, though it could elaborate on the meaning of 'max results'.

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: searching the asset universe by symbol, name, or sector substring, with case-insensitivity noted. This distinguishes it from sibling tools like get_asset (exact retrieval) and list_sectors (enumerating sectors), though it does not explicitly name 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 no guidance on when to use this tool versus alternatives like get_asset or list_sectors. It lacks any conditions, exclusions, or mentions of context where another tool would be more appropriate.

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

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

With no annotations provided, the description carries the full burden and excels: it explicitly warns that settlement runs in sim mode, that no money moves, and that the receipt attests to work, parties, and price—not payment. This is critical, non-obvious behavioral information that prevents misinterpretation.

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 well-structured: a one-line purpose, a focused note on sim mode, and a clean arg list. It is front-loaded with the primary action, and every sentence earns its place 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 the output schema exists, return details are unnecessary. The description covers preconditions ('delivered job'), the source of inputs (hire_agent), and the sim-mode caveat, making it complete for an agent to invoke correctly. No critical operational detail is missing.

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

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

Schema description coverage is 0%, so the description fully compensates by explaining each parameter: job_ref is the job to settle from `hire_agent`, and buyer_token is the token returned by `hire_agent`. This adds meaning far beyond the bare 'string' type 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 opens with a clear, specific verb-resource pair: 'Settle a delivered job and get its signed receipt.' It distinguishes itself from siblings like hire_agent by focusing on the post-delivery settlement step, leaving no ambiguity about its role.

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 context by requiring a 'delivered job' and referencing `hire_agent` for the job_ref and buyer_token, indicating the proper sequencing. However, it does not explicitly state when not to use it or compare with alternatives, though no competing settle tool exists among siblings.

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