Server Quality Checklist

Tool Scores

• control_planeD
  1.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of disclosing behavior. It does not state whether the operation is read-only, whether it has side effects, how pagination works, or what the returned payload looks like. It only lists some registry attributes, which hints at output content but does not reveal operational behavior.

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

  Conciseness2/5

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

  The description is short, but its structure is muddled: 'that is beacon, global pause, blocklist and role registry' is grammatically awkward and mixes abstractions. The colon-separated list is dense and not front-loaded around a clear action, making the sentence harder to parse despite its brevity.

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

  Completeness1/5

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

  With no annotations and no output schema, the description is the only source of context, and it is insufficient. It fails to state the operation, return format, pagination behavior, or how this tool differs from siblings such as 'events' and 'status'. An agent cannot reliably determine how to invoke this tool correctly.

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

  Parameters2/5

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

  Schema description coverage is 0%, and the description does not explain the meaning or effect of the optional 'limit' parameter. The parameter name is somewhat self-explanatory, but the description adds no semantics about which items are limited, how the limit applies, or what the default behavior is.

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

  Purpose2/5

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

  The description identifies the resource (AccessControlsRegistry) and lists data categories such as paused, implementation, blocked-address count, and latest events, but it uses no action verb to state what the tool actually does. The title is nearly a restatement of the description, and it is unclear whether the tool returns, monitors, or modifies registry data; it also overlaps with siblings like 'events' and 'status'.

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

  Usage Guidelines2/5

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

  There is no explicit guidance on when to use this tool versus alternatives. No sibling tools are referenced, no conditions are given, and an agent must infer from the content that this is likely for access-control or registry inspection. This is implied usage at best.

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

• activityC
  2.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It does disclose meaningful behavioral context: data is aggregated 'per UTC day', volume is in 'raw units', and it distinguishes certain transfer classes. However, it never states the return format, whether the operation is read-only, or how the optional 'days' parameter affects results.

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

  Conciseness3/5

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

  The description is a single sentence with a list, so it is compact and free of filler. However, the phrase 'Transfers as economics' is awkward and cryptic, and the sentence packs many metrics into a dense structure that may reduce readability.

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

  Completeness2/5

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

  There is no output schema and no annotations, so the description must explain what the agent should expect. It lists output metrics but not the response shape, time series organization, or the effect of the 'days' parameter. This leaves an agent uncertain about how to interpret the result or set parameters correctly.

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

  Parameters2/5

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

  Schema description coverage is 50% (symbol documented, days undocumented). The description adds no explanation for the 'days' parameter and does not tie the 'per UTC day' phrase to the parameter semantics. It only reinforces the symbol's meaning via 'one asset', so it fails to compensate for the undocumented parameter.

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

  Purpose4/5

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

  The title 'Daily activity for one asset' clearly identifies the resource and scope, and the description enumerates the specific metrics returned (transfers, volume, mints, burns, USDG-settled transfers, non-US-market-hour transfers). This is a specific and informative description, though it does not explicitly differentiate from siblings like 'history' or 'events'.

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

  Usage Guidelines2/5

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

  The description gives no guidance on when to use this tool versus alternatives. It implies use for retrieving daily asset activity, but there is no mention of exclusions, prerequisites, or how it differs from sibling tools such as 'history' or 'holders'.

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

• chain_healthB
  3.4/5.0
  Behavior3/5

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

  There are no annotations, so the description carries the transparency burden. It implies a read-only snapshot through 'latest reading' and lists the key fields returned. However, it does not disclose staleness, units, caching behavior, whether the status page is a link or a text value, or any failure behavior.

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

  Conciseness5/5

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

  The description is a single, tight sentence that front-loads the resource ('Robinhood Chain's latest reading') and then delivers a concrete metric list. Every part earns its place with no filler.

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

  Completeness3/5

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

  For a zero-parameter tool with no output schema, the description reasonably lists the fields an agent can expect. However, it omits additional context that would help an agent fully understand the result, such as freshness semantics, units, formatting of 'status page', and when to prefer this over the sibling 'status' tool.

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

  Parameters4/5

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

  The input schema has zero parameters, and the baseline for zero-parameter tools is 4. The description does not need to explain parameter semantics; it instead productively lists what the returned reading contains.

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

  Purpose4/5

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

  The description clearly identifies a specific health-check resource: Robinhood Chain's latest reading, and enumerates the metrics returned (head block, block time, base fee, L1 block, batch count, delayed messages, batch-poster balance, status page). It does not explicitly distinguish itself from the sibling tool 'status', which could overlap, so it loses a point on differentiation.

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

  Usage Guidelines2/5

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

  No guidance is given about when to use this tool versus alternatives such as 'status' or other chain-related tools. The description implies 'check chain health' but provides no exclusionary or alternative-based usage guidance.

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

• eventsA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description must carry the behavioral burden. It does disclose non-obvious behavior: kind filtering semantics, symbol narrowing, and that since returns only newer rows oldest first with a nextCursor. It does not explicitly state read-only behavior, response shape, or pagination mechanics beyond the cursor mention, but the 'changelog' framing implies a read-only listing.

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

  Conciseness4/5

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

  The description is one dense, front-loaded sentence with no filler. Every clause adds scope or parameter semantics, and the semicolon-separated structure keeps it readable despite its length.

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

  Completeness3/5

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

  For a four-parameter tool with no annotations and no output schema, the description covers event scope and parameter behavior well enough for an agent to invoke it correctly. It still omits the output row shape and any explicit guidance for selecting this tool over related siblings, so it is not fully complete.

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

  Parameters4/5

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

  Schema description coverage is only 25%, but the description compensates well: it explains kind filtering with allowed prefixes, symbol narrowing to one token, and since semantics including ordering and nextCursor. Only limit is left to the schema's min/max constraints, which are fairly self-explanatory.

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

  Purpose4/5

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

  The description opens with 'Authority events' and lists concrete event categories, making it clear this is a changelog/query tool for registry events. It stops short of an explicit verb like 'list' or 'retrieve', and it does not explicitly differentiate from siblings such as activity or history, but the stated scope is specific enough to identify the tool's purpose.

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

  Usage Guidelines3/5

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

  The description gives strong within-tool usage guidance: kind can filter exactly or by prefix, symbol narrows to one token, and since returns newer rows with a cursor. However, it never says when to choose this tool over sibling tools like activity, history, or chain_health, so cross-tool selection must be inferred.

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

• bridgeA
  3.6/5.0
  Behavior4/5

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

  With no annotations, the description carries the full behavioral burden and it does useful work: it defines what the gap means, labels deposits/withdrawals as 'latest', and specifies the seven-day withdrawal window. It does not explicitly state that the operation is read-only, but the observational language and absence of side effects make that clear.

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

  Conciseness4/5

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

  The description is a single dense sentence with no filler—the main output categories are front-loaded and the useful 'value in flight' explanation earns its place. The grammar is slightly compressed, but it remains readable and efficient.

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

  Completeness3/5

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

  The description covers the main output domains and gives one parameter hint, which is helpful for a two-parameter tool with no output schema. Still, it does not clarify how limit applies, what the default output shape is, or how the listed categories are structured, so an agent must infer some invocation details.

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

  Parameters3/5

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

  Schema description coverage is 0%, so the description must clarify parameters; it does add meaning to symbol by saying it narrows the flows. However, the limit parameter is never mentioned, and the precise meaning of 'flows' in the filtering context is left somewhat ambiguous. This is partial compensation at best.

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

  Purpose4/5

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

  The description states the tool reports bridge-specific data: L1 escrow versus L2 supply, recent L2 deposits/withdrawals, and withdrawals past the seven-day claim window. The verb is implicit rather than explicit, but the resource and scope are specific enough to distinguish it from general status or asset-listing siblings.

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

  Usage Guidelines3/5

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

  The domain context (token bridge escrow and flows) makes it clear when an agent would use this tool, and the mention that 'symbol narrows the flows' provides a filtering hint. However, there is no explicit guidance about when to prefer this over alternatives such as status, activity, or history, nor any when-not-to-use conditions.

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

• corporate_actionsA
  3.7/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the behavioral disclosure burden. It clarifies that the data is published by Robinhood and associated with Stock Tokens, which implies a read-only listing. Still, it does not state whether the response is a flat list, whether only in-progress actions are included, or what fields the data contains.

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

  Conciseness5/5

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

  The description is a single compact sentence with key domain terms front-loaded and no filler. The relationship 'each tied to its token' adds useful meaning without bloating the text.

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

  Completeness4/5

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

  For a parameterless endpoint, the description conveys the essential scope: Robinhood-published corporate actions for Stock Tokens. It is not exhaustive about the exact return shape or the 'in progress' aspect from the title, but the low complexity makes the current description largely sufficient for invoking the tool.

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

  Parameters4/5

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

  There are zero parameters and schema description coverage is 100% vacuously, so the baseline of 4 applies. The description's token-relationship context is useful but not necessary for parameter understanding.

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

  Purpose4/5

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

  The description identifies a concrete resource: corporate actions such as dividends and splits that Robinhood has published for Stock Tokens. It is specific and scoped, but it lacks an explicit verb like 'lists' or 'returns' and does not explicitly distinguish itself from sibling tools such as events or history.

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

  Usage Guidelines3/5

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

  The phrasing 'for Stock Tokens' and 'each tied to its token' implies this tool should be used when an agent needs token-specific corporate action data. However, there is no explicit when-to-use guidance, exclusions, or reference to alternative sibling tools.

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

• holdersA
  3.7/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden and excels: it explains null label behavior, unknown address probing, the difference between live and as-of-block shares, the 24-hour job cadence, chain-head readiness, and the fact that small holders make floatPct a floor. This gives an agent the operational context annotations would otherwise provide.

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

  Conciseness4/5

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

  The description is long but densely informative; every sentence covers a distinct semantic point that matters because there is no output schema. It is front-loaded with the core question, though a bulleted or segmented layout would improve scanability.

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

  Completeness4/5

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

  It covers nearly all output semantics, including null conditions, base units, share numerators, and timing. The main gap is the undocumented limit parameter and the lack of an explicit top-level shape, which are important for correct invocation without an output schema.

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

  Parameters2/5

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

  Symbol is documented in the schema and echoed by 'ticker', but the optional limit parameter has no semantic explanation anywhere; the description never says what limit controls. With only 50% schema coverage, the prose should compensate, and it does not.

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

  Purpose4/5

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

  The opening sentence states exactly what the tool returns: how much of a ticker is in investor hands, where the rest sits, and who holds it in descending order. It is clearly scoped to one asset and distinct from sibling resource-specific tools, though it never explicitly names an alternative.

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

  Usage Guidelines3/5

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

  No alternative tools or when-not-to-use conditions are mentioned. The description strongly implies its use for holder and float concentration inquiries and gives readiness timing, but doesn't explicitly compare with siblings like pools or bridge.

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

• issuer_documentsA
  3.7/5.0
  Behavior4/5

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

  With no annotations present, the description carries the full burden and does substantial work: it discloses the returned data (documents, CDN ETag, Last-Modified, token mapping, watched pages, last-change times) and the filtering behavior. It does not explicitly mention pagination, ordering, or read-only semantics, but for a list-style tool this is reasonably transparent.

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

  Conciseness5/5

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

  Two dense sentences convey a large amount of useful detail without filler. The scope, metadata fields, watched pages, and filter values are all presented compactly and front-loaded.

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

  Completeness4/5

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

  For a tool with one optional enum parameter and no output schema, the description covers the main return contents and filtering options well. It lacks explicit guidance on default behavior without a kind value and does not clarify how the watched-pages portion relates to sibling tools, but overall it provides enough context for correct invocation.

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

  Parameters4/5

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

  Schema description coverage is 0%, but the description compensates by explaining that 'kind' is a filter and by listing all valid values exactly matching the schema enum. It does not state what happens when kind is omitted, but for a single optional parameter this is adequate.

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

  Purpose4/5

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

  The description clearly identifies the tool's resource: every document the issuer publishes plus watched pages, with metadata and filtering. It lacks an explicit retrieval verb like 'list' or 'get', and it includes corporate-action content that overlaps with a sibling tool name, but the intent is unmistakable.

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

  Usage Guidelines2/5

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

  No guidance is given for when to use issuer_documents instead of siblings such as corporate_actions, history, or events. The kind filter is explained, but there are no exclusions, prerequisites, or references to alternative tools.

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

• lookalikesA
  3.7/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral burden. It discloses ordering, the three verdict categories, and the impostor criterion ('beacon test'). It does not mention pagination or default limits, but for a read-only listing tool the exposed behavior is reasonably transparent.

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

  Conciseness4/5

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

  The description is a single dense sentence with no filler; each clause contributes meaningful detail about classification, ordering, or filtering. The heavy parenthetical structure keeps it from being maximally scannable, but it is still efficient.

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

  Completeness3/5

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

  The description explains the domain, verdicts, and ordering, but with no output schema it does not sketch the shape of each returned result beyond the verdict. Limit semantics are also left ambiguous, so an agent may not know exactly what to expect from a call.

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

  Parameters2/5

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

  Schema description coverage is only 50%, and the description adds little beyond the symbol parameter by saying 'Filter by symbol.' The limit parameter has no schema description and no mention in the description, leaving its effect and default behavior unexplained.

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

  Purpose5/5

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

  The description clearly defines the resource: ERC-20s that borrow a listed ticker or exact name at another address, and it specifies output ordering ('most held first') and a verdict taxonomy. This makes the tool easy to distinguish from sibling tools like list_assets or get_asset.

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

  Usage Guidelines3/5

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

  The only usage guidance is 'Filter by symbol,' which implies the intended call pattern but does not explain when to prefer lookalikes over list_assets or get_asset. It also does not clarify whether the symbol filter is required or optional in practice.

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

• feed_roundsA
  3.9/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and does well: it states newest-first ordering, the exact output fields, the meaning of 'answer' (price × multiplier in USD), and how 'since' and 'limit' affect results. It does not explicitly declare read-only status, but the query semantics and field listing make that clear enough.

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

  Conciseness5/5

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

  The description is one dense, front-loaded sentence that conveys resource, ordering, output schema, and filter semantics without filler. Every clause earns its place.

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

  Completeness4/5

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

  Given no output schema and no annotations, the description covers the essential return values, parameter behavior, and ordering. Minor gaps remain around response envelope, error cases, and exclusivity boundaries, but for a simple history-fetching tool the core information is present.

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

  Parameters4/5

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

  The description adds meaning beyond the schema: 'since' is described as narrowing to rounds after an ISO instant, and 'limit' is described with a maximum. It fills the gap for 'limit', which lacks a schema description, while 'symbol' is adequately covered by the schema.

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

  Purpose4/5

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

  The description clearly identifies the resource: Chainlink feed rounds for a ticker, and specifies ordering and returned fields. It lacks an explicit verb like 'retrieves' or 'lists', and it does not directly name a sibling for distinction, though the 'Chainlink feed' qualifier helps separate it from generic history tools.

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

  Usage Guidelines3/5

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

  The description implies its use case: when you need Chainlink round history for a ticker. However, it gives no explicit when-to-use versus alternative guidance and no exclusions, leaving the agent to infer context from the title and field names.

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

• list_assetsA
  4.1/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full disclosure burden, and it does well: it discloses the scope (verified assets only), per-asset return contents (multiplier, pauses, Chainlink price, holders, second-source agreement), filter semantics, and the 50-asset enrichment cap. It is silent on pagination, default result limits, and result ordering, which keeps it from a 5.

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

  Conciseness4/5

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

  The description is one dense paragraph but is logically ordered: scope → returned data → filtering → enrichment. The core listing purpose is front-loaded and every clause carries information. It borders on long, but there is no padding given the number of behaviors it needs to convey.

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

  Completeness4/5

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

  For a tool with no output schema and no annotations, the description effectively documents the return payload inline (address, decimals, trust, live state) along with parameter behaviors and a result cap. The main gaps are the unresolved sibling overlap (fields values mirror dedicated sibling tools, with no routing guidance) and the absence of pagination/default-limit behavior.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the schema already documents q, fields, and symbols, giving the baseline of 3. The description adds context for fields (per-asset semantics, the 50-asset cap, and the concentration use case) but largely restates the filter behavior already present in the schema, so it does not meaningfully exceed the baseline.

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

  Purpose5/5

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

  The description states a specific verb and resource ('Every verified asset on Robinhood Chain (chain 4663)') and enumerates exactly what is included: Stock Tokens, bridged coins, USDG, WETH, with contract address, decimals, trust, and live state. It clearly differentiates from the sibling get_asset by being the plural/list variant and distinguishes itself from lookalikes, corporate_actions, feed_rounds, and holders by offering those as optional fields within the list response.

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

  Usage Guidelines4/5

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

  The description explains the two filtering modes (q substring vs. symbols exact tickers) and gives an explicit use case for the enrichment path ('concentration answers which Stock Tokens have the least float in one request'). However, it never names sibling tools as alternatives or states when NOT to use this tool — an agent must infer the boundary against the dedicated lookalikes, corporate_actions, feed_rounds, and holders endpoints.

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

• statusA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It does this well by explaining the meaning of states like 'filling' and 'stalled' and clarifying that these do not indicate wrong or slow data. It does not explicitly mention side effects or access requirements, but for a status tool this is a reasonable disclosure.

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

  Conciseness5/5

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

  The description is dense but every sentence earns its place: it starts with the core purpose, enumerates exactly what is covered, and then gives practical usage and interpretation guidance. No filler or redundant restatement.

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

  Completeness5/5

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

  For a parameterless tool with no output schema, the description is complete enough for an agent to know what to expect and when to call it. It explains all major output categories and the critical interpretation caveats, leaving little ambiguity.

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

  Parameters4/5

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

  The tool has zero parameters, so there is nothing for the description to add beyond the schema. The baseline of 4 applies because the schema already fully covers the parameter surface.

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

  Purpose4/5

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

  The description clearly identifies the tool's resource: freshness of everything Fletch publishes, including daemon heartbeat, registry jobs, scanners, and figure ages. It is specific and not a tautology, though it lacks an explicit verb and does not directly differentiate itself from sibling tools such as chain_health.

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

  Usage Guidelines4/5

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

  It gives explicit guidance on when to call: before trusting a number whose freshness matters. It also explains how to interpret freshness verdicts, which helps the agent know what the result means, but it does not discuss when not to use this tool or when a sibling would be preferable.

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

• dex_venuesA
  4.3/5.0
  Behavior5/5

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

  With no annotations to rely on, the description carries the full burden and does so exceptionally well. It discloses row-per-venue behavior including venues with no pools yet, the meaning of readingHistory/scan position, the floor semantics of counts, the Pons launchpad mapping onto Uniswap v3, and precise definitions for depthUsd, checkedAt, and headAt.

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

  Conciseness4/5

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

  The description is dense but justified: nearly every clause adds needed semantic detail about fields, timing, and edge cases. It is front-loaded with the purpose and trigger conditions, though the long middle sentence could be broken up for easier scanning.

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

  Completeness5/5

  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 and no annotations, the description provides a remarkably complete picture of the tool's return content and interpretation. It covers row identity, field definitions, date windows, edge cases for unread venues, and special launchpad behavior, leaving no major ambiguity for an agent deciding to call it or interpret its results.

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

  Parameters4/5

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

  The input schema has zero parameters, so there is nothing for the description to clarify. The behavior of an unparameterized tool is fully explained, and the description focuses on the output semantics rather than inputs.

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

  Purpose4/5

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

  The description clearly identifies the tool's purpose: enumerating DEX venues on a chain and summarizing their aggregate value and pool/volume metrics. It even gives trigger scenarios ('ask before saying where a Stock Token trades', 'pool count looks implausibly low'), but it does not explicitly name or contrast sibling tools such as pools or activity.

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

  Usage Guidelines4/5

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

  The description state when to use this tool: before claiming where a Stock Token trades, and when a venue's pool count looks suspicious. That is strong context, but it does not provide explicit exclusions or name alternative tools to use instead, so it falls just short of full guidance.

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

• poolsA
  4.4/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden, and it delivers substantial transparency. It explains the exact meaning of depthUsd as a ceiling, clarifies that liquidity is raw in-range L and not a dollar figure, notes null swaps/volume for newly discovered pools, explains v4 vs v3 addressing, and defines discovery states. These are non-obvious behaviors essential to interpreting results.

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

  Conciseness4/5

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

  The description is long, but every sentence carries substantive meaning about field semantics, edge cases, or discovery behavior. The main outcome and ordering are front-loaded, followed by caveats. It could be broken into shorter sentences or bullets for readability, but it is not padded with filler.

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

  Completeness5/5

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

  For a data-rich tool with no output schema, the description is remarkably complete. It specifies the fields returned, the units and semantics of ambiguous metrics, time-window behavior for swaps and volume, v4/v3 structural differences, and discovery-state caveats. The one required parameter is trivially documented, so nothing essential is missing for correct invocation and interpretation.

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

  Parameters3/5

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

  The input schema already documents the only parameter, symbol, with a clear example (TSLA), and coverage is 100%. The description adds context that the symbol is a ticker used to find trading pools, but it does not need to add more because the schema is sufficient for this single-parameter tool.

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

  Purpose5/5

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

  The description names a specific resource (DEX pools for a ticker) and a precise shaping (deepest first in dollars, across all venues the registry reads). It enumerates the returned fields and the special pool used for premium, which makes the tool's purpose unmistakable and distinguishes it from asset-level siblings like get_asset or dex_venues.

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

  Usage Guidelines4/5

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

  The description clearly establishes when to use the tool: to obtain pools trading a given ticker, sorted by dollar depth, across every venue. It does not explicitly enumerate exclusions or alternatives among the sibling tools, but the domain and scope are stated precisely enough that an agent can infer the appropriate context.

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

• get_assetA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It does impressive work, explaining what state.dex contains and how depthUsd semantically differs from raw Uniswap liquidity: 'the figure the deepest pool is chosen by, since Uniswap's raw liquidity compares two pools only when they hold the same pair.' It doesn't state return envelope structure, pagination, or error handling, but given no annotations and the rich existing content, it earns a 4 rather than a 5.

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

  Conciseness4/5

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

  The description is long, but every sentence earns its place: the lead sentence enumerates the data payload, the second gives a use case, and the rest explains a subtle but critical output detail (pool depth vs raw liquidity). The state.dex explanation is slightly dense but still substantive. The description is front-loaded with the tool's purpose before technical nuance.

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

  Completeness4/5

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

  For a single-parameter registry lookup, the description is nearly complete. The tool has no output schema, so explaining what the asset object contains is essential, and it does. The only gap is that it doesn't describe what happens when a ticker has no match or when multiple lookalikes exist, but the presence of the lookalikes field and sibling tool list covers that partially. Overall, the description gives an agent enough context to invoke the tool correctly and understand its response.

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

  Parameters4/5

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

  Schema coverage is 100%, so the schema already documents the ticker parameter. The description adds usage intent ('Use this before writing any address into code') and clarifies that the symbol is a ticker with an example. It also adds meaning to the larger data model (state.dex venue/poolId/depthUsd), which indirectly helps an agent understand output semantics. With complete schema coverage and this additive context, 4 is appropriate.

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

  Purpose5/5

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

  The description opens with a clear, specific statement: 'One asset with everything the registry knows' and then enumerates a comprehensive list of what's included (address, trust, live state, multiplier history, mints/burns, reconciliation, corporate actions, control-plane events, lookalikes, Chainlink rounds). It also explicitly identifies the ticker parameter, so an agent can immediately distinguish this from siblings like list_assets or history.

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

  Usage Guidelines5/5

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

  The description gives direct usage guidance: 'Use this before writing any address into code.' This tells an agent when to invoke the tool and implies its role as a foundational verification step. It also distinguishes the tool from siblings by explicitly referencing the pools tool: 'The pools tool names the venue of every pool, that one included' — a clear pointer to an alternative for pool-level lookups.

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

• historyA
  4.8/5.0
  Behavior5/5

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

  Discloses critical behavioral traits beyond raw schema: each row is a single reading at takenAt, not a daily open/close/average; the job runs hourly and rewrites the current day's row; coverage reports days on record and history starts when the snapshot first ran; null means 'not read that day' rather than zero. It also explains unit semantics for dexPremiumPct and totalSupplyRaw and the ERC-8056 multiplier difference between Chainlink price and bid/ask. There are no annotations to contradict.

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

  Conciseness4/5

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

  The description is dense and information-rich, front-loading the core purpose and then providing necessary caveats and unit semantics. A few sentences are long, but every sentence earns its place given the complexity of the data. It could be slightly tightened, but remains efficient for the volume of behavioral nuance it conveys.

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

  Completeness5/5

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

  Completeness is strong given the tool's complexity and the absence of an output schema. The description explains the row's meaning, time semantics, coverage, and key unit differences. While it doesn't enumerate every output field in prose, the schema already covers parameter definitions and the example plus field list adequately set expectations.

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

  Parameters4/5

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

  Schema coverage is already high (83%), and the description adds semantic detail for the 'at' parameter with an example, explains the window with from/to or days, and clarifies the meaning of 'coverage' and 'fields'. It does not restate the standard string formats, but the example and explicit date-window hints give the agent meaningful extra context.

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

  Purpose5/5

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

  The description clearly states the tool returns a daily snapshot per asset with an explicit list of fields, and uses a concrete example query ('what was TSLA's premium on that day') to show how to use the at parameter. It distinguishes this from related tools by specifying it is historical daily data, not status or feed rounds.

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

  Usage Guidelines5/5

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

  Provides explicit guidance on when to use the tool: to answer questions about a past day's values per asset, with at=YYYY-MM-DD, from/to or days for a window, and fields to narrow rows. It also clarifies the data's daily nature, coverage caveats, and the distinction between reading takenAt versus a daily open/close/average. It doesn't explicitly name sibling alternatives, but its context is strong enough to route an agent correctly.

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

• webhooksA
  4.9/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden and does so thoroughly. It discloses the authentication failure mode, key routing constraints, signature format, and the subtle semantics of lastError versus lastDeliveredAt, preventing misinterpretation.

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

  Conciseness5/5

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

  The description is long but every sentence earns its place, moving from what the tool returns, to auth, to exclusions, to signature and error semantics. There is no filler or repetition.

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

  Completeness5/5

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

  For a no-parameter, no-output-schema tool, this is complete: an agent knows what it will get, how to authenticate, what it should not use it for, and how to interpret ambiguous fields. Nothing needed for correct invocation is missing.

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

  Parameters4/5

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

  The tool has zero parameters and the schema covers 100% of them, so there is no parameter semantic gap. Per the 0-param baseline this is a 4; the description also adds relevant context about environment variables that affect invocation.

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

  Purpose5/5

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

  The description identifies the tool as a read-only representation of the account's registered webhook endpoints for watcher alerts, including per-endpoint delivery and error state. It clearly distinguishes this from sibling tools by domain (webhooks vs assets/chain health/status) and explicitly says creation/rotation/deletion is not exposed here.

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

  Usage Guidelines5/5

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

  It states auth prerequisites (FLETCH_API_KEY with watchers:read, 401 without key, HTTPS-only delivery) and gives explicit when-not guidance: endpoint lifecycle operations are deliberately not exposed, with the dashboard and POST /api/v1/webhooks named as alternatives. This lets an agent route to the correct operation.

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