LiquiLens — the Failure Radar

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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses key behavioral details: 'Display-only: feeds no institution score and no watchlist tier', 'used_in_regime and used_in_transmission are always false', 'Channels that cannot be read are listed in cannot_see, never reported as calm', and the default vs full output payload. These are non-obvious traits that help the agent interpret results and side effects.

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

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

The description is longer than a simple two-sentence summary, but each sentence contributes distinct information: the core question, channels covered, exclusions, behavioral caveats, and output format. It is front-loaded with the main purpose and avoids fluff, though slight redundancy exists ('Answers ONE question' vs 'Read the Corporate Transmission board...'). Overall well-structured for a complex dashboard tool.

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

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

Despite having no output schema, the description thoroughly explains what the tool returns: a TRANSMISSION verdict, divergence read, cannot_see channel list, and context channels. It also covers default vs full output, flags that are always false, and how missing channels are reported. For a tool of this complexity, the description is self-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?

The only parameter 'full' is already fully documented in the input schema with its effect and default. The description mentions the same ('pass full:true for thresholds, per-leg basis and method prose') but adds no new meaning. Since schema coverage is 100%, the baseline of 3 applies.

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

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

The description opens with a precise statement of what the tool answers: 'whether FUNDING stress is reaching nonfinancial FIRMS' and explicitly differentiates from sibling tools ('not banks (failure_radar_board), not households (household_credit_board), not money-market plumbing'). This satisfies a specific verb+resource+scope and distinguishes from alternatives.

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

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

The description explicitly states when to use the tool by naming what it covers and what it does not, and points to a specific alternative for oil context ('use Seiche's oil_funding_context for the full live-vs-reference oil architecture'). It also clarifies that this board is display-only and does not feed institution scores, informing whether it fits the user's need.

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 idempotentHint; the description reinforces with 'Read', 'display-only', and 'takes no arguments'. It adds context about the cited nature and the deferral to the detail route, plus the disclaimer about scores/advice. 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?

Three sentences: the first defines the tool's output, the second routes to the detail endpoint, and the third clarifies constraints. Each sentence is purposeful and information-dense 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 absence of an output schema and arguments, the description does well to enumerate the content categories and the limits of the tool. It also points to the detail route for deeper data, which provides a complete context for when this compact register is sufficient.

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

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

The input schema is empty and the description explicitly states 'Takes no arguments,' which aligns with 100% schema coverage. With zero parameters, there is no additional meaning to add beyond this.

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

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

The description opens with a specific verb ('Read') and resource ('compact cited bank/crypto exposure register'), then enumerates the contained categories (quantum, stablecoin/venue links, exposure channels, run-risk flags). It clearly conveys what the tool does and distinguishes from detailed disclosure routes, even though it doesn't name a specific sibling tool.

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

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

The description implies when to use this tool—when you need the compact exposure register—and explicitly directs users seeking detailed disclosures to the public REST detail route. It also states what the tool is not for ('never an institution score or investment advice'). However, it doesn't explicitly compare to sibling board tools.

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

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

The description adds meaningful context beyond annotations: it reveals the data source ('public REST detail route'), lists the displayed metrics, and explicitly states it does not feed institution scores. The readOnlyHint and idempotentHint already cover safety, so the description enriches with output-related behavior. It could mention rate limits or auth, but for a read-only board this is sufficient.

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

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

The description is compact: two sentences that pack the purpose, content listing, technical route, and disclaimers. No filler or redundancy. Front-loaded with the verb 'Read' and the board name.

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 zero-parameter read-only tool with no output schema, the description fully covers what the agent needs: it enumerates all returned fields, states the data source, and clarifies limitations. There is no missing detail that would prevent correct use.

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

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

The tool has zero parameters, so the baseline is 4. The description accurately states 'Takes no arguments', which is redundant with the empty schema but harmless. No parameter semantics are needed beyond the baseline.

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

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

The description clearly specifies a read action on the 'compact BTC/ETH Crypto Regime board' and enumerates its exact contents (change-point state, log-SR statistic, last shift, observation count, cross-read). This distinguishes it from sibling boards like crypto_exposure_board and stablecoin_rails_board by naming unique data elements.

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 to read this specific board and notes it 'feeds no institution score and is not investment advice', which provides a negative boundary. However, it does not explicitly compare with sibling tools or state when to prefer this over alternatives, leaving usage guidance mostly implied.

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

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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses two distinct output modes (summaries without arguments vs full case file with per-quarter table) and a provenance guarantee that figures are audited against primary filings. This adds meaningful behavioral context without contradicting 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 compact and front-loaded, with no redundant sentences. The opening verb and resource are immediate, and all subsequent details (case list, audit, argument behavior, cohort caveat) serve 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 single-parameter read-only tool with no output schema, the description thoroughly covers both the default return (all seven verdict summaries) and the single-file return (per-quarter table). The cohort caveat prevents misuse, and no prerequisites or edge cases are left unaddressed.

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

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

The schema already fully documents the optional slug parameter, but the description adds the seven valid case names as implicit slug values, making parameter selection easier. Since no enums exist, this compensation is valuable and goes beyond the schema's example.

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

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

The description opens with the verb 'Read' and identifies the exact resource: seven European case files, listing each by name and outcome category (failed, stressed survivors, control). This clearly differentiates it from sibling tools like evidence_us and evidence_india.

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

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

It implies use for European case evidence and explicitly warns not to treat it as a cohort or quote a European recall percentage, providing a clear when-not. However, it does not name alternative tools explicitly, so it stops short of fully satisfying the 'alternatives' criterion.

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 substantial behavioral context beyond annotations: it explains the data sourcing (filing-availability proxy, +60-day delay), the limitation that overwritten amendments are unreconstructable, and that rigor artifacts are never trimmed. This informs the agent about data caveats and the nature of the output, which the read-only/idempotent annotations do not cover.

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

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

The description is dense but well-structured, with each sentence earning its place. It front-loads the core purpose and then provides necessary details and an explicit pointer to the sibling tool. No waste or redundancy.

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

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

Given the tool has no parameters and no output schema, the description fully compensates by enumerating the contents (verdicts, lead times, uncertainty intervals, rigor artifacts) and noting data limitations. It is complete for the agent to understand what to expect without any additional structured metadata.

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

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

The tool has zero parameters, and the schema is an empty object. The description explicitly states 'Takes no arguments,' which is the only needed semantic and aligns with the baseline score of 4. It adds clarity beyond the schema by confirming no input is required.

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 reads a full Indian crisis diagnostic, specifying the scope (48 institutions, two decades) and content (verdicts, lead times, uncertainty intervals, rigor artifacts). It distinguishes itself from the sibling tool evidence_institution by positioning this as the full diagnostic, making the purpose unambiguous.

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

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

The description explicitly tells the user when to use this tool versus the alternative: 'Use evidence_institution for one institution's complete replay.' This provides clear context and a direct exclusion, so the agent knows this tool is for the full diagnostic and when to go elsewhere.

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, idempotentHint=true, and openWorldHint=false, covering safety and idempotence. The description adds meaningful context about what the replay includes, such as 'first-alert bookkeeping' and 'plain verdict line,' going beyond a bare read-only statement and giving the agent a detailed expectation of the returned content.

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 exactly two sentences, front-loaded with the main action 'Read' and immediately enumerating the data items. The second sentence is a clear directive for the prerequisite step. Every word earns its place; no fluff or repetition.

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

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

For a single-parameter read-only lookup, the description is complete: it names the exact resource, lists all relevant data components, and explains the prerequisite relationship to evidence_india. No output schema exists, but the description sufficiently specifies what will be returned.

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

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

The schema already documents the single 'slug' parameter with a description and example, so baseline is 3. The description adds value by instructing the agent to obtain the slug from evidence_india, providing a concrete lookup path that the schema alone doesn't convey.

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

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

The description states a specific verb ('Read') and resource ('one Indian institution's complete construction-PIT crisis replay'), enumerating the contents (scored quarterly trajectory, dossier rows, alert bookkeeping, verdict line). It clearly distinguishes from sibling evidence_india by explicitly pointing to it as the list-first step.

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 'Call evidence_india first to list the replayed institutions and their slugs,' giving a concrete prerequisite and alternative. The India-specific scope and 'one institution' nature further clarify when this tool is appropriate versus siblings like evidence_europe or evidence_markets.

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 idempotentHint=true, and the description adds useful context: the tool takes no arguments, returns only a headline rather than full details, and deliberately omits a cohort claim for Europe. This gives the agent a clear behavioral expectation beyond the safe-read annotation.

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 purposeful sentences: the first states the action and scope, the second gives usage guidance and drill-down paths. No wasted words, well front-loaded.

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

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

For a zero-parameter, no-output-schema tool, the description is complete: it states the purpose, enumerates the covered markets, clarifies precision ('headline' vs full record), and names the sibling tools for deeper access. No important gap remains.

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

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

The tool has zero parameters, so the baseline is 4. The description reinforces 'Takes no arguments' and adds meaning by specifying exactly which markets and diagnostic types are covered, which is the only relevant semantic context.

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 the specific verb 'Read' and resource 'historical-evidence headline' with three markets enumerated, clearly distinguishing this from sibling drill-down tools (evidence_india, evidence_us, evidence_europe). It explicitly frames this as the entry-point 'headline' view, which differentiates it from the 'full record' 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?

Explicit guidance is provided: 'Start here when asked what LiquiLens has tested, then drill into evidence_india, evidence_us or evidence_europe for the full record behind each headline.' This states when to use and names the alternatives, plus notes the Europe limitation ('deliberately no cohort claim').

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 goes well beyond the read-only/idempotent annotations by disclosing the watchlist is budgeted (top decile), not an institution-level verdict, and explicitly notes the inclusion of misses (e.g., fraud-driven miss, seven named misses) to avoid misinterpretation. This provides crucial 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 dense but each sentence adds value: purpose, performance metrics, included replays/misses, and semantic caveat. It is front-loaded with the main verb and resource, though the statistical details could be trimmed without losing core guidance.

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

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

With no output schema, the description explains what content to expect (scores, replays, misses, scoreboard) and the semantic caveat. It lacks explicit return format but is otherwise sufficient for a read-only diagnostic tool.

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

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

The only parameter, include_trajectories, is fully documented in the schema with default and description. The tool description adds no extra parameter context, but schema coverage is 100%, so the baseline of 3 applies.

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 reads a specific diagnostic ('US bank current-amended-vintage diagnostic') and describes its content: every FDIC-insured bank scored quarterly, replayed against 552 failures with performance metrics. It distinguishes from sibling tools via 'US' and 'historical diagnostic' in the title and description.

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 when one needs the US bank watchlist diagnostic, but it does not explicitly mention when not to use or alternatives. There is guidance on interpretation ('Read the semantics before quoting') but no direct comparison to sibling tools.

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

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

Annotations already mark readOnlyHint and idempotentHint. The description adds that it takes no arguments and outputs are research screens, not credit ratings, providing useful 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?

Concise yet rich: one sentence on purpose, one listing fields, one on usage, one on output nature. Front-loaded with key information, no wasted words.

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

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

Given no output schema, the description details the output fields comprehensively (risk metrics, statuses). Could mention row count or sort order, 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?

No parameters, and schema coverage is 100%. The description fully compensates by explaining the purpose and output fields in detail.

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 reading the live Failure Radar board for India, listing institutions with various metrics. It explicitly contrasts with the sibling 'failure_radar_institution' for individual dossiers.

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 to call this first to discover institution slugs, then use failure_radar_institution for details. Lacks explicit when-not-to-use context but is sufficient.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description's role is lighter. It adds behavioral context about absent dossiers being reported as absent and not scored from memory, which is useful but does not go beyond what annotations indicate.

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 sentence that front-loads the main action and list of outputs. Every clause adds value, with 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?

For a tool with one parameter and no output schema, the description provides enough context: what the dossier contains, how to call it, and what happens for missing entries. It also references the prerequisite tool. Minimal 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 only parameter 'slug' has 100% schema coverage with a clear description and example. The description adds context by linking it to 'failure_radar_board rows', which enhances understanding 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 the specific verb 'Read' and identifies the resource as 'the full radar dossier for one Indian institution', listing detailed components (per-quarter score, failure-PD trajectory, etc.). It distinguishes from the sibling tool 'failure_radar_board' by instructing to call that first for valid slugs.

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 instructs to call 'failure_radar_board first to discover valid slugs', and states that an institution without a vetted dossier is reported absent and never scored from memory. This provides clear when-to-use and expected outcomes.

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 critical withhold discipline (60 observed days before odds are given, accrued count stated) and 'Counted, never fitted' — behavior not present in the readOnly/idempotent hints. This explains how results are computed and why absence is not precision. The readOnlyHint is consistent with 'display-only 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 appropriately sized and front-loaded, with each sentence covering a distinct aspect (what, how, withhold discipline, argumentlessness, state impact). Minor redundancy with readOnlyHint, 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?

Despite no output schema, the description specifies the output contents (transition matrix, reach odds, accrued count) and the exposure threshold, making it self-contained for an agent to invoke. It could add exact output structure but is largely complete for a parameterless read 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 zero parameters, so per the baseline the description need not add parameter detail. It does state 'Takes no arguments,' which reinforces the schema's empty properties object.

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

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

The description opens with a specific verb ('Read') and resource ('Markov forward odds for every state-bearing public-signal layer'), then details exactly what's returned: a transition matrix and empirical k-day reach odds. It clearly distinguishes from sibling tools by emphasizing 'Display-only context, never a state driver.'

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

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

The description provides clear context: use this to read empirical forward odds. 'Never a state driver' and 'Takes no arguments' signal when not to use it (for state changes or parameterized queries). However, it does not name a specific alternative tool among the siblings, so it lacks an explicit 'use X instead' pointer.

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 idempotent=true; the description adds meaningful context: 'Display-only: feeds no institution score and no watchlist tier', 'Channels that cannot be read are listed in cannot_see, never reported as calm', and the 'falling never scores' rule. It also clarifies default vs full payload behavior, going 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?

The description is dense but every sentence contributes: scope, alternatives, data sources, methodology caveats, and return format. It is front-loaded with the core question and structured logically, though slightly long. It earns a 4 rather than a 5 due to minor redundancy (e.g., 'US HOUSEHOLD' and 'household balance sheets' repeated).

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 carries the full burden of explaining return semantics, and it does so: 'Returns ~4KB slim by default; pass full:true for thresholds, method prose and full sparklines.' It also explains what data is included, what is unscored context, and how missing channels are handled, making it complete for a read-only board tool.

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

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

The single boolean parameter 'full' has 100% schema coverage with a description in the schema. The tool description echoes the same information ('pass full:true for thresholds, method prose and full sparklines') without adding new constraints or value 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?

The description opens with 'Answers ONE question: whether stress is reaching US HOUSEHOLD balance sheets' — a specific verb, resource, and scope. It explicitly contrasts with siblings (corporate_transmission_board, failure_radar_board, Seiche money-market plumbing), making the purpose unambiguous.

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

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

Provides explicit guidance: 'Read the Household Credit board: is stress transmitting through US household balance sheets?' and clearly states what it is not for (not firms, not banks, not money-market). It also notes the tool is display-only and does not feed scores or watchlist tiers, helping agents decide when to avoid it.

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

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

The description adds substantial behavioral context beyond the readOnly/idempotent annotations: it never guesses scores, never turns uncovered names green, and clarifies that the SHA-256 is not attestation or proof of publication time. This is valuable disclosure of limitations and semantics.

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

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

The description is compact yet information-dense. Three sentences cover purpose, input constraints, output contents, and critical caveats without redundancy. Every sentence contributes unique meaning.

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

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

For a tool with a single parameter and no output schema, the description tells the agent what the packet contains (canonical values, URLs, lens bases, hashes) and warns about the hash's limitations. This is sufficient for correct invocation and expectation setting.

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

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

The schema only says 'exact Failure Radar slug or full institution name.' The description adds 'or one unique case/punctuation-normalized full name' and explicitly states 'never fuzzy-matches,' giving the agent precise guidance on acceptable input forms and rejection behavior.

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

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

The description opens with a specific verb+resource: 'Build the compact human-review handoff for one fresh-vetted Indian Failure Radar institution.' It clearly distinguishes this from siblings by specifying the India scope and the exact-match-only behavior, contrasting with search/evidence 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 states when to use the tool (for a fresh-vetted Indian institution with an exact slug/name) and explicitly says 'never fuzzy-matches,' implying you must already know the exact identifier. It does not name alternative tools but gives strong contextual boundaries.

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?

Beyond the annotations (readOnlyHint, idempotentHint), the description adds key behavioral details: results are newest first, each item includes the RBI's source URL, and it gracefully handles missing data by returning a note instead of silence.

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

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

The description is a single sentence that efficiently conveys purpose, content, ordering, and error handling. Every part earns its place without redundancy.

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

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

Despite no output schema, the description explains what items contain (specific enforcement types and source URL) and handles the empty state. This is complete for a simple read-only tool with zero 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 no parameters and 100% schema coverage, the description confirms the tool takes no arguments, which is sufficient. No additional parameter details are 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?

The description clearly states the tool reads the latest RBI enforcement actions, specifies the types (monetary penalties, licence cancellations, supervisory directions), source (rbi.org.in press releases), and ordering (newest first). It naturally distinguishes from sibling tools like evidence_institution or evidence_india by focusing on RBI supervisory 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?

The description implicitly indicates this tool is for fetching RBI enforcement data but does not explicitly state when to use this tool versus alternatives like evidence_india or evidence_markets. It clearly notes it takes no arguments.

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 establish readOnlyHint=true and idempotentHint=true, so the read-only nature is covered. The description adds meaningful behavioral nuance: 'the full oracle state never treats partial evidence as CALM' exposes a domain rule about evidence handling, and the compatibility note about the retained peg/run alert clarifies the tool's relationship to older endpoints. It also includes a disclaimer that the board is not investment advice. These go beyond the structured hints.

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

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

The description is three sentences: the first defines the board's content, the second points to a more detailed route, and the third covers arguments, behavioral rules, and a disclaimer. There is no wasted wording; every clause serves a distinct purpose, and the main verb+object is front-loaded.

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

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

The board is complex, and the description covers its key facets without an output schema. It enumerates the tracked evidence categories, states that full data is available on the REST route, clarifies no arguments are expected, and discloses a behavioral rule about CALM. This is sufficient for an agent to decide whether to call the tool and what to expect.

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

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

With zero parameters, the schema has full coverage and nothing to explain. The description explicitly states 'Takes no arguments,' which removes any ambiguity about invocation. This is the expected baseline for a no-parameter tool and adds just enough clarity.

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

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

The description opens with a specific verb 'Read' and clearly identifies the resource as the 'Stablecoin Rails board.' It then enumerates the board's distinct scope—peg, redemption-run, liability validation, reserve evidence, chain concentration, tripwire state, and aggregate regime—which differentiates it from sibling boards like crypto_exposure_board or household_credit_board. This is a precise and non-generic purpose statement.

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

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

The description provides context on when to use this tool: it is a compact read-only board, while 'Series and full receipts stay on the public REST detail route' signals that granular data is served elsewhere. It also notes that the separate peg/run alert is retained for compatibility, implying this board is an aggregate view. However, it does not explicitly name or contrast sibling tools, so it falls just short of a 5.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, indicating safe, read-only operation. The description adds that results are 'verbatim from the public record,' aligning with annotations. No contradictory or additional behavioral context (e.g., rate limits) is provided.

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

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

Three sentences cover purpose, parameter guidelines, and return behavior with no redundancy. Every sentence adds value, making it highly efficient.

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

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

The description fully explains the tool's search capability, required parameters, behavior with empty q, and return fields. Given the absence of an output schema, it adequately describes the output format. No gaps remain.

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

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

All four parameters have descriptions in the schema, and the description adds contextual details like 'case-insensitive substring,' 'exact RBI classification as it appears,' and the constraint to provide at least one filter. This goes beyond the schema alone.

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

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

The description clearly states the verb 'Search' and the resource 'RBI's official register of NBFCs', specifying search by substring and optional filters. It distinguishes itself from sibling tools (evidence, failure radar, etc.) by focusing on a specific register.

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

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

The description provides clear guidance on required parameters ('Give at least one of q, classification or layer') and hints at browsing behavior ('an empty q with a filter browses that whole slice'). It does not explicitly compare to sibling tools or state 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 provide readOnlyHint and idempotentHint. The description adds valuable behavioral details: server-side execution, returning the verifier's verdict verbatim, and including even unflattering results. This goes beyond annotations to clarify the tool's transparency and integrity-checking nature.

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

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

The description is only two sentences, front-loaded with the core action. Every clause adds meaning: the first sentence details the verification process, the second clarifies the purpose and usage context. No redundant words or extraneous details.

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 a single parameter, no output schema, and no nested objects, the description is fully complete. It covers purpose, behavior, output nature (verdict verbatim), and usage context. No gaps remain for an agent to infer.

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 'stream', which has a clear name and description in the schema. The tool description does not add additional parameter-specific information beyond what the schema provides. Baseline score of 3 is appropriate as the schema sufficiently documents the parameter.

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

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

The description clearly states the tool independently verifies a ledger stream by recomputing hash-chained commitments, checking signatures and anchors. It uses specific verbs ('verify', 'recompute', 'check') and resource ('published record'). It distinguishes from siblings like evidence tools and failure radar, which focus on retrieval or alerts, not cryptographic verification.

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

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

The description explicitly says 'Use this to check whether the published early-warning track record is tamper-evident and intact,' indicating when to use. It does not explicitly state when not to use, but the context and sibling tools imply it is for verification rather than lookup or analysis. No direct mention of alternatives, so slightly below perfect.

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