the-floor

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

Annotations already indicate read-only and open-world behavior. The description adds behavioral specifics: definitions of the four flow types, exclusion of liquidity, and the metric playerSellShare context. No contradictions with annotations.

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

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

The description is concise, fitting key concepts into a few sentences. The opening question is a good front-load. However, it could be slightly more structured (e.g., bullet points) but is not overly long.

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

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

Given the tool has no parameters and no output schema, the description adequately covers what the tool does and how to interpret its output. It explains the metrics and warns about common mistakes, making it complete for its simplicity.

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

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

There are no parameters in the schema, so parameter semantics are not needed. The description does not attempt to document parameters, which is appropriate given 100% schema coverage and zero parameters.

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

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

The description clearly states the tool answers 'Do desk owners reinvest or dump?' by splitting FLOOR flow into four categories. It specifies the resource (FLOOR flow) and action (splitting into behavioral buckets), and implicitly differentiates from sibling get_ tools that fetch different data.

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

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

The description advises to 'Use these buckets' and warns against deriving sells from raw pool transfers to avoid double-counting. This provides clear context on proper usage, though it lacks explicit when-not-to-use statements.

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

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

Annotations provide readOnlyHint and openWorldHint, but description adds valuable context: 'null means unknown, never zero' and lists exact return fields, enhancing transparency beyond annotations.

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

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

Single sentence structured with colon-delimited list of fields. Front-loaded with purpose, no extraneous words.

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

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

Given no output schema, description adequately explains return fields and null behavior, covering complexity of multiple attributes.

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

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

Schema already describes id parameter (100% coverage), but description reinforces the range '1-4444' and associates it with broker token id, adding minor value.

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

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

Description clearly states 'One StonkBroker by id' and lists specific return fields, distinguishing from siblings like get_brokers (plural) and other specific getters.

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?

Clear when to use: to fetch a single broker's details. While no explicit when-not or alternatives, the sibling tools provide context for specific queries (e.g., floor status), implying this is the general getter.

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

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

Annotations already indicate readOnlyHint and openWorldHint. Description adds significant behavioral context: handles upgrade credit, drop rate varies, dilution, token price movement. No contradiction.

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?

Compact yet comprehensive. Front-loaded with core purpose, includes essential details and warnings. No unnecessary sentences.

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

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

Despite no output schema, the description adequately explains what is returned (fees, dividends, payback days) and provides necessary caveats. Complete for this tool's purpose.

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

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

Schema coverage is 100%, but description adds meaning: explains that 'id' provides an exact on-chain fee quote and that omitting it yields table prices. For 'tier', it clarifies that omission shows all five tiers. Enhances understanding beyond schema.

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

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

Clearly states it computes activation math for brokers, specifying verb 'get' and resource 'broker activation math'. Distinguishes from siblings like get_broker (general info) and prepare_activate_broker (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?

Provides clear guidance on when to use the 'id' parameter for exact quotes vs omitting for table prices, and includes cautions about assumptions. However, does not explicitly contrast with sibling tools for when not to use.

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

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

Annotations already indicate readOnlyHint and openWorldHint; description adds binding rule about desk vs liquid contents permanence, which is valuable behavioral context beyond annotations. No contradictions.

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

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

Two sentences, no wasted words: first describes purpose and output, second explains key behavioral rule. Front-loaded with essential information.

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

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

Despite lacking output schema, the description explicitly lists returned fields (wallet, owns desk, desk state). The binding rule provides necessary caveat. Complete for a read-only tool with one parameter.

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

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

Schema coverage is 100% with one parameter 'id' clearly described. Description does not add extra parameter meaning beyond the schema, so baseline score of 3 is appropriate.

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

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

Explicitly states the tool's function: checking if a StonkBroker's ERC-6551 wallet plays The Floor and returns desk state. Clearly distinguishes from sibling get tools like get_floor_state or get_broker by focusing on cross-game floor status.

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

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

Implied usage: use to determine if a broker participates in The Floor game. No explicit when-not or alternatives mentioned, but the context of sibling tools makes differentiation clear.

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

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

Adds significant detail beyond annotations: explains that contents are a removable snapshot, activation is cleared on transfer, and Floor desk survives sales. Aligns with readOnlyHint and openWorldHint while disclosing dynamic 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?

Description is concise and front-loaded with the ranking formula, but the important framing notes are packed into a single dense paragraph. Could be slightly clearer with separate sentences, but no wasted words.

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

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

Given the simple read-only interface (one optional param, no output schema), the description fully explains the ranking basis and caveats. Provides enough information for an agent to use 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?

Single parameter (limit) with 100% schema description coverage. Description does not add further meaning beyond the schema. Baseline score of 3 is appropriate.

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

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

Clearly states it provides a leaderboard of activated StonkBrokers ranked by current wallet USD value (dividend stocks + $STONKBROKER + ETH). Distinguishes from siblings like get_broker or get_leaderboard by specifying the ranking metric and scope.

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

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

Includes 'IMPORTANT framing' notes that clarify the data's transient nature and how it should be interpreted (not an appraisal). This provides context for appropriate use, though it doesn't explicitly state when to use versus alternatives.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds valuable behavioral context: ~10-minute cadence, ETH value per round, and details on what the tool returns (price, burns, Floor-crossover count). This goes beyond the annotations.

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

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

Two sentences that are informative but somewhat dense with jargon (e.g., 'ERC-6551 wallet', 'tokenized stock'). Could be slightly more concise, but no unnecessary words.

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

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

Given no output schema, the description covers the main return elements (minted, holders, activation tier, dividends, price, burns, Floor-crossover count). It also explains the broader context (ERC-6551 wallets, tokenized stock). Missing details like pagination or data structure, but adequate for a zero-parameter tool.

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

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

No parameters exist in the input schema, so there is nothing to explain. Baseline is 4, and the description does not need to add param info.

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

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

The description clearly states it retrieves the entire StonkBrokers collection state in one call, listing specific metrics (minted/holders, activation tier census, etc.). This distinguishes it from numerous sibling tools like get_broker, get_broker_floor_status, etc.

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 comprehensive state call for the collection but does not provide explicit guidance on when to use this tool versus alternatives like get_broker or get_broker_leaderboard. No exclusion criteria or alternative recommendations are given.

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

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

Annotations already provide readOnlyHint and openWorldHint. Description adds behavioral context by naming the specific return components (tier counts, alpha concentration). For a tool with no output schema, this is helpful.

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

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

Single sentence, 17 words, no fluff. Front-loaded with key purpose.

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

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

For a simple tool with no parameters and no output schema, the description adequately explains what is returned. Could mention that it's aggregate data, but that is implied by 'across players'.

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

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

No parameters; schema coverage is trivially 100%. Baseline for 0 params is 4. No additional param info needed.

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

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

Description clearly states what the tool does: shows distribution of desks and alpha across players, specifically tier counts and alpha concentration (top 1% / top 10%). Distinguishes from sibling get_* tools which focus on other aspects.

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?

Implicitly indicates usage for understanding distribution, but no explicit when-to-use or when-not-to-use guidance. Sibling tools are not mentioned.

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 adds the fact that results are 'ranked by alpha', which is behavioral context beyond the annotations. However, with readOnlyHint and openWorldHint already declared, the description provides minimal additional transparency (e.g., no mention of pagination, data freshness, or potential 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 two sentences long, directly stating the output contents and ordering. It is front-loaded with the key noun and efficient with word choice.

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 should fully describe the return format. It mentions firms, members, contributions, and free agents, but not the structure (e.g., fields, nesting). Given the tool's moderate complexity, this is adequate but incomplete.

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

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

There are no parameters in the input schema, so the description does not need to explain parameters. According to the rubric, 0 parameters yields a baseline of 4.

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

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

The description states the tool returns firms, members, contributions, and unaffiliated free agents ranked by alpha. This is clear enough given the tool name 'get_firms', and it distinguishes from sibling tools focused on brokers, floors, etc. However, it doesn't specify what 'alpha' refers to, leaving some ambiguity.

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

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

No guidance is provided on when to use this tool versus alternatives. While the sibling list is large, the description does not mention any conditions, prerequisites, or exclusions.

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

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

Annotations already declare readOnlyHint and openWorldHint, so the description adds value by enumerating returned fields. No contradictory statements, but does not disclose data freshness or any other behavioral traits beyond the 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?

Two sentences with zero wasted words. First sentence lists all key data points; second sentence provides usage guidance. Front-loaded and efficient.

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

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

Given zero parameters, readOnlyHint, and no output schema, the description sufficiently explains what the tool returns (list of fields). It could note if the data is live or cached, but for a simple read operation, it is complete enough for agent to use correctly.

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

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

No parameters exist, so schema coverage is 100% and baseline is 4. Description adds no param info because none are needed; the tool requires no input.

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 uses specific verb ('get') and resource ('floor state') and lists concrete data fields (price, market cap, etc.). Clearly distinguishes from siblings like get_broker or get_behavior, which focus on specific aspects.

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?

Explicit states 'Start here for context' indicating it's the entry point. Does not list when-not-to-use or alternatives, but the sibling tools are more specialized, making the usage context clear.

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

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

The description adds significant context beyond annotations: it explains that rows before live tracking are reconstructed and marked seeded:true, and that missing metrics should be treated as unknown, not zero. This is valuable behavioral information.

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

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

The description is two concise sentences with no wasted words. It is front-loaded with the core purpose and adds necessary nuance in the second sentence.

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

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

Despite no output schema, the description fully explains the return data: daily snapshots of specified metrics, with handling for reconstructed rows and missing values. It is complete for a read-only tool with no parameters.

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

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

With zero parameters, the description doesn't need to explain parameters. It adds meaning by describing the output data (daily snapshots, specific metrics). Schema coverage is 100%, so baseline is 3, but the excellent output description justifies a 4.

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

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

The description clearly states the tool provides daily snapshots for trends with specific metrics (price, market cap, etc.). It distinguishes itself from sibling tools like get_live_actions or get_holder by focusing on historical data.

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

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

The description implicitly indicates it is for retrieving historical trend data. While it doesn't explicitly state when not to use it or compare to alternatives, the context of sibling tools makes its purpose clear.

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

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

Annotations already declare `readOnlyHint` and `openWorldHint`, which inform the agent of safe, read-only behavior. The description adds that the tool returns top holders 'by balance', implying sorting, but does not explain pagination or any other runtime behavior. With annotations covering safety, the description adds minimal extra 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 a single concise sentence that directly states the tool's purpose. It is front-loaded with the key verb and resource, and every word is necessary. No waste.

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

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

Given the tool has no parameters and no output schema, the description is reasonably complete. It specifies the ranking criterion (balance) and the entity (holders). However, it could clarify what $FLOOR refers to, and whether the list is limited or ordered. Overall, it provides adequate context for a simple read-only tool.

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

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

There are no parameters (schema coverage 100%), so the description does not need to explain parameters. It instead describes the output (top holders by balance), which adds value beyond the empty schema. This 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 the tool as returning top $FLOOR holders by balance, using a specific verb and resource. It distinguishes itself from sibling tools like `get_brokers` or `get_firms` by focusing on holders. However, the token symbol ($FLOOR) is not explained, slightly reducing clarity.

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

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

No guidance is provided on when to use this tool versus its many sibling tools. The description does not mention prerequisites, alternative tools, or scenarios where this tool is appropriate, leaving the agent to infer usage from context.

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

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

Annotations indicate read-only and open-world behavior. Description adds behavioral detail: recruiter is fixed forever at desk creation. No contradiction with annotations.

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

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

Two succinct sentences with no redundant information; first sentence captures main function, second adds relevant detail.

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 list tool, the description explains what the response contains (ranked wallets by alpha and top recruiters) and why the recruiter is fixed, providing sufficient context without an 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 coverage is 100% with one parameter (limit) already described. Description adds no additional meaning beyond the schema, meeting the baseline for high coverage.

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

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

Clearly states the tool returns wallets ranked by alpha and top recruiters by referrals, distinguishing it from sibling tools like get_broker_leaderboard.

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

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

Implies usage for obtaining leaderboard rankings but does not provide explicit guidance on when to use this tool versus alternatives such as get_broker_leaderboard.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds context by specifying the scope ('recent on-chain game actions') and listing action types, which is consistent and helpful. No contradictions.

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

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

The description is extremely concise—a single line listing action types. Every word is meaningful, with no repetition 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?

Given the tool has only one optional parameter, no output schema, and annotations indicate safe read-only behavior, the description sufficiently covers what the tool returns and its scope. No gaps.

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

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

The input schema fully documents the 'limit' parameter with description and range. The tool description adds no extra meaning beyond the schema, so baseline score of 3 is appropriate.

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

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

The description clearly states the tool returns 'Recent on-chain game actions' and lists the types, making the purpose clear. It distinguishes from sibling tools like 'get_firms' which return different data, though it doesn't explicitly contrast.

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. It doesn't mention prerequisites, filters, or comparisons to sibling tools like 'get_history' or 'get_floor_state'.

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?

Description adds important behavioral context: fields may be null due to upstream scan failures, and null means unknown not zero. This complements the readOnlyHint and openWorldHint annotations by explaining data fidelity and interpretation.

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

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

Two sentences with no wasted words. The first sentence enumerates the data fields, the second provides critical behavioral context. Perfectly concise and 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 lists many output fields and addresses null handling, making it mostly complete for a read operation. Could additionally specify the output structure or mention that it is a single object, but overall sufficient.

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

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

Schema description coverage is 100% for the single parameter 'address'. The description does not add any additional meaning beyond what the schema already provides, meeting the baseline expectation.

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 lists specific fields returned for a wallet, making it clear what the tool does. It distinguishes from sibling tools by focusing on player wallet data, but could be improved with an explicit action verb like 'retrieve' or '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?

No guidance on when to use this tool vs. alternatives (e.g., get_behavior, get_broker). The description does not provide context for selection or exclusion, leaving the agent without decision criteria.

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

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

Description adds extensive context beyond annotations: lists exact tokens, mentions live prices and pool liquidity, warns about empty pools and copycat tokens, and explains the pricing nuance (USDG vs WETH). 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?

Front-loaded with main purpose, but the warning section is dense and could be more structured. Still, every sentence provides value and the overall length is justified by the complexity.

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

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

Given no parameters and no output schema, the description covers the tool's output thoroughly, including real-world usage pitfalls and references to other tools for 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?

No parameters; baseline 4. The description fully explains what the output contains and adds meaning beyond the empty schema by detailing the return fields and important caveats.

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

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

Description clearly states the tool returns information about three specific dividend stocks (AAPL/AMZN/NVDA): symbol, address, decimals, live USD price, and Uniswap V3 pools. It distinguishes from siblings like get_broker which returns complete holdings.

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

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

Explicitly states this is NOT the full set of tokens a broker can hold, and directs users to get_broker for complete holdings. Also provides warnings about pricing and copycat tokens, guiding appropriate use.

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

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

Description adds significant behavioral context beyond annotations: states ignored halving decay (best case), notes facts and paybacks are not instructions, and requires the wallet to have a desk. Annotations (readOnlyHint, openWorldHint) are complemented well.

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

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

Description is verbose but every sentence adds value, listing specific metrics and constraints. It is front-loaded with purpose. Could be slightly more concise but efficient for the amount of detail.

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 fully compensates by enumerating all returned data points and constraints (ignoring halving decay, desk requirement). Completely adequate for an agent to understand what the tool provides.

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

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

Schema coverage is 100% for the single parameter (address). The description does not add new information beyond '0x wallet to analyze' already in the schema. Baseline 3 applies as description adds minimal value over schema.

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

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

Description clearly states the tool provides decision-relevant math for one wallet, listing specific data points (alpha/share, floor earned, pending PnL, headroom, desk upgrade, operator payback, halving countdown). It distinguishes from sibling getters like get_behavior or get_broker by focusing on strategy metrics for wallet-level reasoning.

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

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

Explicitly states the tool is for reasoning about the next move and requires the wallet to have a desk. However, it does not explicitly mention when not to use this tool or list alternatives, though the sibling context provides many other getters.

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

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

Annotations already indicate readOnly and openWorld. Description adds valuable behavioral context: warns about thin liquidity and that large buys move price. No contradiction.

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

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

Two sentences, front-loaded with key information, no verbose or redundant phrases.

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 info tool with no parameters and no output schema, the description is fully complete: it lists all returned data elements and adds a practical warning.

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

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

No parameters exist, so baseline is 4. Description does not need to add 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 states it provides all necessary info for swapping ETH↔FLOOR, including router, WETH, pool, fee tier, and spot price. It distinguishes itself from sibling tools like prepare_swap_eth_for_floor.

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

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

Explicitly advises to read this before prepare_swap_eth_for_floor or to construct/verify a swap yourself, providing clear usage context.

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

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

Annotations already declare readOnlyHint=true. The description adds the positional nature of ids and the off-by-one warning, plus details of returned fields (name, cost, alpha, bandwidth). No contradictions with annotations.

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

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

Two sentences, no filler. Front-loaded with key information. Every word earns its place.

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

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

Given no parameters and no output schema, the description fully explains what the tool returns and why it's needed. References a sibling tool for context. Complete for this complexity level.

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

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

No parameters exist (0 params, 100% schema coverage). The description adds meaning about the output fields, which is valuable given no output schema. Baseline 4 for zero parameters is appropriate.

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

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

The description clearly states that the tool lists operators (catalogue) with id, name, cost, alpha, bandwidth. It explicitly links to the recruiting workflow and distinguishes ids from sibling tools like prepare_recruit_operator. Verb+resource is specific.

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

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

The description instructs 'Read this before recruiting' to pick the right id, warning about off-by-one errors. It provides clear context for when to use, though lacks explicit when-not-to-use or alternatives. Still strong 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?

The description reveals numerous behavioral traits beyond annotations: verification-gated operation, error behavior, fee distribution (50% burned, 50% treasury), automatic approval handling, and the critical note about NFT transfers clearing activation. Annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) are consistent and not contradicted.

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

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

The description is a single, focused paragraph. Every sentence provides unique value: core function, error conditions, fee handling, and the critical usage warning. It is front-loaded and efficient with no unnecessary fluff.

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

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

Given high complexity and no output schema, the description is thorough on behavior and conditions but lacks details about the output format (e.g., structure of the returned calldata). However, it mentions 'returns no calldata unless...' implying success output, which is helpful but not fully explicit.

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

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

Schema coverage is 100% but the description adds essential context: the 'from' parameter is mandatory for allowance check, 'tier' 5 yields 3.33x dividend weight, and auto-inclusion of 'approveFirst' when allowance is insufficient. This enriches the schema's basic 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 builds unsigned transactions to activate or upgrade a StonkBroker at a tier. It uses specific verbs ('build', 'activate', 'upgrade') and distinguishes itself from sibling tools (e.g., prepare_collect, prepare_swap) by focusing on broker activation. The 'VERIFICATION-GATED' prefix adds clarity.

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

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

The description explains when to use the tool (after any planned NFT transfer, not before) and the conditions for success (on-chain checks pass, allowance sufficient). It also notes the 'from' wallet must pay, and that approveFirst is included automatically. This 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?

Annotations provide readOnlyHint=false, openWorldHint=true, destructiveHint=false. The description adds that it builds an unsigned transaction and approves an exact amount by default, not unlimited. This adds behavioral context beyond annotations, though it could mention if approval overwrites existing allowances.

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

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

The description is two sentences long, front-loading the purpose and immediate usage context. Every sentence adds value without redundancy. It is concise and 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 that there is no output schema, the description explains the core function and its role in the workflow (required before recruiting/upgrading). However, it does not explicitly describe what the tool returns (an unsigned transaction message), leaving a minor gap for agents unfamiliar with 'prepare' tools.

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

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

Input schema has 100% coverage with descriptions for both parameters (from and amount). The description reinforces 'pass `amount` in whole FLOOR', which is already in the schema. No additional semantics beyond the schema are provided, so baseline score of 3 is appropriate.

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

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

The description clearly states it builds an unsigned ERC20 approve for FLOOR, specifying the verb 'Build', the resource 'UNSIGNED ERC20 approve', and the purpose 'letting the game contract spend your FLOOR'. It also mentions it's needed before recruiting or upgrading, distinguishing it from other 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 explicitly says 'Needed before recruiting or upgrading', providing clear context for when to use. It also explains the default behavior of exact amount and how to pass the amount parameter. While it doesn't list exclusions, the guidance is sufficient for proper usage.

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

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

Annotations indicate destructiveHint=false and readOnlyHint=false, but the description adds key behavioral context: verification-gated, conditional error (no calldata if conditions not met), and that collected floor belongs to the NFT (not the user). This supplements the annotations well.

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

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

The description is concise at two sentences, front-loaded with key qualifier ('VERIFICATION-GATED'), 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 the complexity of the tool (blockchain transaction), the description covers purpose, verification requirements, and outcome. It does not describe return format, but that may be standard. It sufficiently differentiates from sibling tools.

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

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

Schema coverage is 100%, but the description adds meaning to the 'from' parameter by stating it is the broker's current owner and is verified on-chain. This clarifies usage beyond the schema description.

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

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

The description clearly states that the tool builds an unsigned transaction to collect pending PnL from a Floor desk to the broker's wallet. It uses specific verbs ('build', 'collect') and distinguishes from siblings with 'VERIFICATION-GATED' and 'UNSIGNED transaction'.

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

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

The description states conditions for successful use: 'from' must match ownerOf on-chain and wallet must have a desk. It also advises using 'executeCall' for further actions. However, it does not explicitly differentiate when to use this tool versus similar siblings like prepare_collect or prepare_broker_floor_desk.

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 thoroughly discloses behavior: it errors and returns no calldata unless all on-chain checks pass; it lists the checks (activation, ownership, no existing desk); it notes the transaction is unsigned and that 0.01 ETH rides along; it explains the referrer behavior. Annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) are consistent, and the description adds significant context beyond them.

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 verbose but well-structured. It front-loads the main action and then provides necessary detail (checks, rationale, referrer info). Some phrases like 'nobody on the chain has done it yet' are extraneous but do not harm clarity. Overall, it earns its length with valuable information.

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

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

Given no output schema, the description explains what happens on success (returns unsigned transaction) and on error (returns no calldata). It covers prerequisites, behavior, and side effects. The only minor gap is not specifying the exact format of the return value, but for a transaction-preparation tool this is acceptable.

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

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

The description adds meaning to the 'from' parameter by explaining it must match ownerOf and is verified on-chain, and for 'referrer' it explains defaults and permanence. However, the description states 'from' is REQUIRED, while the input schema lists 'from' as not required (only 'id' is required). This contradiction reduces the reliability for an agent. Schema coverage is 100%, so baseline is 3, but the discrepancy lowers the score within that tier.

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 builds an unsigned transaction to open a desk on The Floor for a StonkBroker's ERC-6551 wallet. It specifies the verb ('build'), the resource ('unsigned transaction'), and the unique context ('VERIFICATION-GATED cross-game move'). This distinguishes it from sibling 'prepare_' tools by focusing on desk opening and the verification-gated nature.

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

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

The description provides clear conditions for use: the broker must be activated, the 'from' address must be the owner, and the broker must not already have a desk. It also explains the benefits (second income stream, transferability with NFT). However, it does not explicitly contrast with alternatives or state when not to use this tool, though the checks implicitly guide the user to activate first if needed.

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

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

Discloses key behaviors beyond annotations: verification-gated, return of calldata only on success, possibility of returning an approveFirst transaction, and the requirement for the owner to sign. Annotations only indicate non-read-only; the description adds rich behavioral context.

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

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

The description is a single dense paragraph (~150 words). It contains all necessary information but lacks scannability (no bullet points or breaks). Could be slightly more structured for easier reading, but is not verbose.

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

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

Covers preconditions (verification), parameters (detailed guidance), behavior (return of calldata and optional approveFirst), and post-conditions (nothing signed). Lacks explicit output structure but compensates with clear error handling description. No output schema, so this is adequate.

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

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

With 100% schema coverage, baseline is 3. The description adds meaning: explains how pool, minAmountOut, and slippagePct interact, warns about decimals mismatch, and clarifies that from is verified on-chain. This adds significant 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 uses specific verbs and nouns: 'build the UNSIGNED Uniswap V3 swap' for a specific wallet type (ERC-6551) on a specific chain (Robinhood Chain). It clearly distinguishes from sibling tools (e.g., prepare_activate_broker, prepare_approve_floor) which handle other actions.

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

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

Provides explicit conditions: 'Errors with no calldata unless from matches ownerOf', 'Refuses to build a swap with no price floor', and explains when to use pool vs minAmountOut. Also notes that nothing is signed or broadcast, guiding the agent to expect the owner to sign later.

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

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

Annotations indicate non-read-only and non-destructive, but the description adds valuable context: 'Free (no FLOOR, no ETH beyond gas)' and 'UNSIGNED transaction', which clarifies cost and that the tool does not execute the transaction. No contradictions with annotations.

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

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

The description is extremely concise: two sentences that cover purpose, cost, and a usage hint. Every word adds value with no redundancy.

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

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

The tool lacks an output schema, and the description does not specify what the returned unsigned transaction looks like (e.g., format, fields). While it implies the output is a transaction, the absence of details leaves some ambiguity for the agent.

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

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

Schema coverage is 100% for the single optional parameter 'from', and the schema description already explains its purpose. The description does not add further parameter meaning beyond the schema, so a baseline score of 3 is appropriate.

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

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

Clearly states the tool builds an unsigned transaction to collect desk's pending PnL. The verb 'Build' and specific resource (unsigned transaction for collecting pending PnL) are unambiguous, distinguishing it from sibling 'prepare_' tools like prepare_broker_floor_collect.

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

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

Explicitly advises to use get_player first to check pendingPnL, establishing a clear precondition. While it doesn't list when not to use or alternatives, the sibling group makes the context clear, and the instruction is sufficient for typical use.

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

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

Discloses key behaviors: builds unsigned transaction (server never sees keys), costs 0.01 ETH, referrer cannot be changed, defaults to dashboard address. This adds significant context beyond annotations.

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

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

The description is well-structured and front-loaded, but contains a few redundant details (e.g., 'this server never sees, holds, or asks for a private key' could be more concise). Still efficient.

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

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

Covers all essential aspects: cost, return format, referrer behavior, immutability, and security. Given no output schema, the description fully compensates by explaining what the tool returns.

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

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

Describes both parameters: 'from' allows checking existing desk, 'referrer' explains omission vs zero address. Adds meaning beyond the schema's 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 it builds an unsigned transaction to open a desk (join the game). It is distinct from sibling tools like prepare_activate_broker which are for different actions.

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 explains when to use (to join the game) and provides critical guidance about the referrer being immutable and needing to inform the user. However, it does not explicitly mention when not to use this tool versus alternatives.

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

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

The description discloses key behaviors: it spends FLOOR, requires prior approval, may produce an approveFirst transaction, and 75% is burned. This goes beyond the annotations (which only provide hints) and fully informs the agent of the tool's 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?

Three sentences are tightly packed with essential information, front-loaded with the core action. No redundant phrasing; every sentence serves a purpose.

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

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

For a simple tool with 2 parameters and no output schema, the description covers all necessary aspects: what it does, prerequisites, error handling (approveFirst), and side effects (burning). It is fully complete for the agent to use correctly.

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

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

Schema coverage is 100%, so baseline is 3. The description enriches the 'from' parameter as the signing wallet and the 'operatorId' as zerobased with examples, adding meaningful context beyond the schema's own 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 builds an unsigned transaction to recruit an operator by ID, using zerobased ids from list_operators. It also mentions spending FLOOR and the burning mechanic, making the purpose highly specific and distinguishable from other 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 explains prerequisites like requiring ERC20 approval and provides guidance on handling short allowances with an approveFirst transaction. However, it does not explicitly state when not to use this tool compared to other prepare_* tools, though the context makes it clear.

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

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

The description adds behavioral context beyond annotations: it clarifies the tool builds an unsigned transaction (not executing it) and notes there is no FLOOR cost. Annotations already indicate non-read-only and non-destructive, but the description adds important nuance about transaction state and cost.

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 at two short sentences, front-loading the core action. Every word adds value, with 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?

Given the tool's simplicity (one optional parameter, no output schema), the description is nearly complete. It explains the action, the target, and a key property (no cost). It could mention the return value (presumably a transaction object) but is adequate for the complexity level.

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

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

The input schema has 100% coverage for its single optional parameter 'from', which is described in the schema. The tool description does not add further meaning to this parameter, so it meets the baseline without extra value.

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

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

The description clearly states the tool builds an unsigned transaction to recruit the free starter operator. It specifies the action (build unsigned transaction), the target (free starter operator), and a unique feature (no FLOOR cost), distinguishing it from sibling tools like prepare_recruit_operator.

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

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

The description implies the tool is used for recruiting the free starter operator, but it does not explicitly state when to use this vs alternative recruitment tools (e.g., prepare_recruit_operator). There is no guidance on prerequisites or exclusions, leaving the agent to infer context.

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

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

Annotations indicate readOnlyHint=false and destructiveHint=false. The description adds that the transaction is 'UNSIGNED', meaning it is prepared but not executed. This provides useful context beyond annotations but does not detail what happens after signing, required permissions, or failure modes. No contradiction with annotations.

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

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

Two sentences are concise and front-loaded. The first sentence states the primary action and purpose; the second adds a constraint. No redundant or vague wording.

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

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

The description lacks details on the output (the unsigned transaction), prerequisites (owning a desk, sufficient bandwidth), and what happens after signing. Given no output schema and the tool's complexity, more context would be helpful for an AI agent to invoke it correctly.

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

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

Schema coverage is 100%, so the baseline is 3. The description explains the tokenId parameter as a 'FLOOROP operator NFT token id' and connects it to seating at a desk. This adds meaning beyond the schema's description. The 'from' parameter is not mentioned, but it is optional and self-explanatory.

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 action: 'Build the UNSIGNED transaction to seat an operator you own... at your desk, so it starts earning alpha.' It specifies the operator is identified by FLOOROP NFT token id and that it must be owned. This distinguishes it from siblings like prepare_unseat_operator and prepare_recruit_operator.

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

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

The description mentions a key condition: 'Seats and bandwidth are limited by your desk tier.' This implies when the tool might be constrained but provides no explicit guidance on when to use it over alternatives or when not to use it. No exclusions or alternative tools are named.

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

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

Annotations already indicate readOnlyHint=false and openWorldHint=true. The description adds critical warnings about real money risk, thin pool, and the need to verify numbers. It also discloses that an approval transaction may be automatically included if from is provided and allowance is insufficient, which is beyond annotation scope.

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

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

The description is a single, well-structured paragraph. The core function is stated first, followed by clear step breakdown and a prominent warning. Every sentence earns its place, 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?

Given no output schema, the description suffices by explaining the tool's role in the buy flow, parameter behavior, and risk. It does not detail the return value, but that is acceptable without an output schema. The only minor gap is not explicitly stating that the result is an unsigned transaction object, but the warning to verify before signing implies it.

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

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

Schema coverage is 100%, so baseline is 3. The description enhances understanding by explaining that amountEth is in whole ETH and requires pre-wrapped WETH, that recipient should be the signing wallet, and that slippagePct defaults to 2%. It also clarifies the from parameter's role in triggering an approval step, adding value beyond 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 builds an unsigned Uniswap V3 swap to buy FLOOR with WETH. It identifies the tool as step 3 in the buy flow and explicitly says the reverse sell is not built here, distinguishing it from siblings like 'prepare_wrap_eth' and 'prepare_approve_floor'.

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 specifies when to use (as the final step after wrapping and approval) and when not to (selling FLOOR for ETH is reversed). It also mentions prerequisites like holding WETH and the optional approval step, providing complete context for decision making.

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

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

Annotations indicate it is not read-only (readOnlyHint=false) and not destructive (destructiveHint=false). The description adds that it builds an unsigned transaction (needs signing) and frees seat/bandwidth, providing behavioral context beyond annotations.

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

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

The description is a single, clear sentence with no wasted words. It efficiently conveys the tool's purpose.

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

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

The description adequately explains the tool's function for a simple transaction builder with two parameters. It does not detail post-actions (signing/sending), but given the tool's scope and sibling context, it is sufficiently complete.

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

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

Schema coverage is 100%, and the description repeats the parameter description for tokenId from the schema without adding new meaning. The 'from' parameter is not elaborated. Baseline score of 3 is appropriate as the description adds minimal value over the schema.

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

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

The description clearly states the tool builds an unsigned transaction to unseat an operator, specifying the verb 'build' and resource 'unsigned transaction to unseat operator'. It distinguishes from siblings like 'prepare_seat_operator' by indicating the opposite 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 implies usage for unseating an operator but does not explicitly state when to use this tool versus alternatives like 'prepare_seat_operator' or prerequisites. With many sibling tools, more explicit guidance would improve clarity.

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

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

Discloses that the tool builds an unsigned transaction, spends FLOOR, and may require prior approval. Annotations (readOnlyHint=false, destructiveHint=false) are consistent; description adds value beyond them.

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

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

Two sentences, front-loaded with purpose and constraints. Every sentence adds value. No redundancy or unnecessary detail.

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

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

Given low complexity (2 optional params, no output schema), the description covers purpose, behavioral traits, parameter usage. No explanation of return value, but acceptable since tool prepares a transaction.

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 100% coverage with basic descriptions. The description adds meaningful context for costFloor: 'pass costFloor from the desk table if you want the allowance checked against the exact price'. No extra for 'from' parameter but overall enhances 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?

Description clearly states verb 'Build the UNSIGNED transaction to upgrade your desk to the next tier'. It distinguishes from siblings like 'prepare_create_desk' by specifying upgrade. The constraint 'always steps up one tier' adds specificity.

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 that it always steps up one tier and that an approve may be needed first. Suggests passing costFloor for allowance check. Lacks explicit when-not-to-use or alternatives, but sibling context partially covers.

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

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

Annotations already indicate readOnlyHint=false and destructiveHint=false. The description adds that it returns a WETH.deposit() call carrying ETH as value, clarifying it's a transaction preparation, not execution.

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

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

A single sentence with a parenthetical explanation. It is front-loaded and contains no fluff, making it easy to parse quickly.

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 simple input (one parameter, no output schema), the description fully explains the tool's purpose and its place in the buying FLOOR workflow.

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

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

Schema coverage is 100% with a clear description for amountEth. The tool description reinforces that it's whole ETH but doesn't add significant new meaning beyond the schema.

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

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

The description clearly states the tool builds an unsigned transaction to wrap ETH into WETH, specifying it's step 1 of buying FLOOR. This distinguishes it from sibling prepare tools like prepare_swap_eth_for_floor.

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

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

The description explains the context (router swaps WETH, not raw ETH) and mentions it's step 1, implying usage before swapping. However, it lacks explicit when-not-to-use or alternatives.

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