California Bitcoin

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

Annotations already signal read-only, open-world, idempotent, and non-destructive behavior, so the bar is lower. The description adds useful behavioral context: free with no account required, deterministic answers, use of integrity-checked primary-source dossiers for covered historical questions, and the suggestion to use it before paying for deeper research.

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 mostly economical and front-loaded with the key facts: FREE, no account, concise deterministic answer, and usage boundaries. The repeated 'FREE. FREE,' opening and the somewhat opaque 'Evaluate California Bitcoin' phrase add minor noise, but the structure remains clear and scannable.

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

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

For a one-parameter tool with full schema coverage, an output schema, and rich annotations, the description is largely complete: it covers cost, account requirements, answer quality, fallback behavior, and sibling distinction. The 'California Bitcoin' reference is slightly unexplained, but it does not block correct invocation.

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

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

Schema coverage is 100% and the single query parameter is already described as 'Bitcoin question to answer from maintained California Bitcoin knowledge.' The description reinforces the query's purpose but does not add much parameter-specific meaning beyond what the schema provides, so the baseline 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 identifies a specific verb and resource: it returns a concise, deterministic answer to a Bitcoin question using maintained knowledge. It also distinguishes itself by noting the special historical-attribution dossiers and names what it is not, such as the evidence-synthesis and claim-verification 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: use for straightforward learning and explanation, and use answer_bitcoin_question_with_evidence for difficult synthesized evidence or verify_bitcoin_claim for proposition adjudication. This gives an agent clear routing logic among siblings.

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 (readOnly, openWorld, idempotent, non-destructive), the description discloses payment cost, evidence sourcing, classification behavior, contradiction handling, confidence, provenance, locators, and explicit uncertainty. This adds rich behavioral context that the annotations alone do not provide, with no contradiction.

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

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

The description is dense and front-loaded with the most important context, including cost and the core deliverable. The long feature list is somewhat enumerative, but each listed capability adds decision-relevant information for an agent. It is appropriately sized for a complex tool, though not maximally concise.

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 a rich output schema, complete parameter schema, and detailed annotations, the description fills in the remaining context: when to use the tool, what distinguishes it from simpler lookups, and what behavioral guarantees to expect (evidence, confidence, uncertainty). Nothing essential for correct invocation is missing.

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

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

Schema coverage is 100% and the query parameter is well-described in the schema, so the baseline is 3. The tool description adds meaning by characterizing the query as 'difficult open-ended' and excluding 'simple learning or single-proposition adjudication,' which clarifies acceptable inputs beyond the schema's minimal description.

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

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

The description clearly states the tool's action: 'Get a compact, source-backed answer to a difficult natural-language Bitcoin question' using an evidence system. It also differentiates from siblings by contrasting with 'retrieve topics or search results' and signaling a specialist, evidence-grounded role rather than a simple lookup. This is a specific verb+resource with clear scope.

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

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

The description explicitly says when to use the tool: 'Use for difficult open-ended Bitcoin questions requiring compact evidence synthesis,' and when not to use it: 'Do not use for simple learning or single-proposition adjudication.' It does not name an alternative sibling tool explicitly, but the exclusions are clear enough to guide selection.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable context beyond annotations: 'deterministic research package' and 'preserving per-item verdict and evidence-quality semantics' clarify the behavior for a batch operation, and the cost disclosure ('PAID 0.50 USD via MPP') is a unique transparency addition. No contradictions with annotations.

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

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

The description is three sentences, each earning its place: cost, purpose, usage guidance, and a negative constraint. It is front-loaded with the most critical detail (paid, batch limit) and avoids redundancy. Extremely tight and efficient.

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

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

The description covers purpose, usage, and key behavioral traits, and an output schema exists to handle return-value details. It omits specifics about partial failures or invalid item handling, but given the annotations and output schema, an agent has enough context to call the tool correctly. Slightly incomplete around edge-case behavior.

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 already fully describes the 'items' parameter with 100% coverage, including types, constraints, and examples. The description does not add new parameter-level semantics beyond what the schema provides; it only restates that items can be claims/questions/evidence requests. Given schema coverage, a baseline 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 states a specific verb ('Process'), resource ('up to 20 distinct Bitcoin claims, questions, or evidence requests'), and outcome ('preserving per-item verdict and evidence-quality semantics'). It clearly distinguishes this batch tool from single-item siblings by emphasizing 'multiple distinct research items in one invocation' and explicitly warns against wrapping a single item, which separates it from answer_bitcoin_question or verify_bitcoin_claim.

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 given: 'Use when the caller has multiple distinct research items in one invocation rather than one question, claim, timeline, or evidence request.' It also provides a negative constraint: 'Do not wrap a single item merely to use the batch product.' This directly tells an agent when to select this tool over alternatives without ambiguity.

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 annotations: it discloses a cost ('PAID 0.10 USD via MPP') and describes the temporal semantics and evidence quality guarantees of the output. This is genuinely useful information that cannot be inferred from readOnlyHint, openWorldHint, or the schema.

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

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

The description is compact and efficiently front-loads the cost and core function before giving usage boundaries. There is a minor redundancy between 'Use for chronological...' and 'Use when chronology is the primary output,' but each sentence otherwise earns its place.

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

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

With a full input schema, annotations, and an output schema present, the description supplies the missing decision and cost context: when to invoke it, what the output emphasizes, and that it is a paid but non-destructive read-only operation. Nothing an agent needs to select and invoke the tool correctly is missing.

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

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

The input schema has 100% description coverage for all four parameters, including examples and bounds, so the description does not need to explain parameter details. The description adds only the general notion of 'query-specific' chronology, which is consistent with the query parameter but does not meaningfully exceed 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?

Names a specific verb and resource ('Build a query-specific chronological Bitcoin research timeline') and clarifies what the output distinguishes: event dates, source dates, effective dates, source-level support, exact locators, and re-verification boundaries. This clearly differentiates it from the sibling research tools, which are not timeline-focused.

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

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

Explicitly states when to use the tool ('chronological protocol or history questions where ordering and temporal semantics are the primary job') and when not to use it ('Do not use for a general explanatory answer where dates are incidental'). This gives an agent a clear decision rule for selecting it versus the answer-oriented 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 declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds valuable non-schema context: the tool is free, requires no account or payment, and does not rerun research or authorize payment. These behavioral traits go beyond the structured annotations and are valuable to an agent deciding whether to invoke the tool.

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

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

The description is mostly efficient and front-loads key operational facts, but it opens with a redundant 'FREE. FREE, no account and no payment' phrasing. The core purpose follows quickly, and the imperative 'Use only with...' is direct. Minor redundancy prevents a perfect score.

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 two-parameter, read-only, idempotent check tool with an output schema, the description adequately covers purpose, prerequisites, exclusions, and the source of valid parameter values. There is no significant missing context that would prevent an agent from calling the tool correctly.

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

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

Schema description coverage is 100%, and both checkpointId and expectedDigest have their own descriptions and format constraints. The tool description reinforces that both values must come from prior research results, but it adds little beyond what the schema already documents.

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 precise operation: compare a previously returned evidence checkpoint against the current dossier digest before deciding whether to rerun or repurchase research. It clearly distinguishes itself from the sibling research and verification tools by stating what it does not do (does not rerun research or authorize payment).

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

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

Explicitly states when it should be used: a repeat caller with a checkpoint and digest from prior California Bitcoin research wants to know whether the dossier changed. It also gives exclusions, saying it does not rerun research or authorize payment, and says to use it only with checkpoint id/digest from prior results.

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 read-only, idempotent, open-world behavior. The description adds meaningful behavioral context beyond them: the tool is paid ('PAID 0.25 USD via MPP'), deterministic, and produces a detailed dossier rather than a lightweight answer. No contradiction with annotations.

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

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

The description is dense and front-loads the action and cost, followed by usage guidance. The two 'Use for...' / 'Use when...' clauses are somewhat redundant, and the long clause list in the first sentence could be tightened, but there is no real filler.

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

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

For a complex research-dossier tool, the description covers purpose, cost, output scope, and the key alternative. An output schema exists, so not describing the return structure is acceptable. It is complete enough for an agent to select and invoke it correctly.

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

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

Schema description coverage is 100%, and the single 'query' parameter is documented as a difficult Bitcoin research question requiring deeper multi-source grounding. The description largely repeats that framing without adding format, constraints, or extra semantics, so baseline 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 states a specific verb ('Produce') and resource ('a deeper deterministic multi-source Bitcoin research dossier') and enumerates what it contains. It also distinguishes itself from a compact-answer sibling by name ('For a compact difficult answer use answer_bitcoin_question_with_evidence instead').

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 gives explicit conditions: use when a broader multi-source dossier is required or a compact direct answer is insufficient, and names the alternative for the compact case. This leaves little ambiguity about when to choose 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?

Annotations already declare read-only, open-world, idempotent, and non-destructive behavior. The description adds a cost signal ('PAID 0.15 USD via MPP') and clarifies that the tool emits evidence components rather than a final narrative answer, which is meaningful behavioral context 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 well-structured and front-loaded with the cost signal before moving into purpose and usage. It is slightly redundant, repeating 'supporting, conflicting, and contextual evidence' and using 'focused' multiple times, but it remains reasonably tight and readable.

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 one-parameter, read-only tool with an output schema, the description covers purpose, usage boundaries, expected evidence content, cost, and what it will not do. Nothing critical for tool selection or correct invocation is missing, and the output schema handles return-value details.

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 query parameter is fully described in the schema (coverage 100%), so the baseline is 3. The tool description adds value by emphasizing that the query should be a focused research question the agent already knows, which helps agents scope their input appropriately.

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 names a concrete deliverable ('focused Bitcoin evidence package') and enumerates its contents: source material, atomic claims, conflicts, source authority, exact locators, caveats, provenance, and temporal scope. It also distances itself from tools that produce final specialist answers or narrative dossiers, so an agent can distinguish it from siblings like answer_bitcoin_question and verify_bitcoin_claim without opening their schemas.

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 gives explicit when-to-use conditions: the agent already knows the research target and primarily needs compact, focused evidence rather than a synthesized verdict. It also provides when-not-to-use signals ('rather than a verdict or narrative dossier', 'without asking California Bitcoin to compose the final specialist answer'), though it does not name alternative sibling tools explicitly.

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, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds value by disclosing that the tool is free/no-account, returns a single canonical topic, and includes sources, provenance, and related concepts.

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 short and front-loads the most important facts, but 'FREE. FREE, no account required.' is redundant and could be condensed. The rest is efficient and useful.

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?

This is a simple one-parameter tool with a full output schema and annotations covering idempotence and safety. The description fully explains when to invoke it, what it returns, and how it differs from search and paid evidence packaging.

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

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

Schema coverage is 100%, and the schema already documents the id format, pattern, max length, and canonical nature. The description reinforces that the id must be a canonical topic id rather than free text, but it adds no format details 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 a specific verb ('Retrieve') with a precise resource ('one canonical Knowledge Atlas topic with sources, provenance and related concepts'). It explicitly contrasts with free-text search, distinguishing it from search_bitcoin_knowledge.

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

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

The description clearly states when to use it: 'Use only when the canonical topic id is already known.' It also gives the decision context ('before deciding whether paid evidence packaging is necessary') and an explicit exclusion: 'Do not use this as free-text search.'

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, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it is free, requires no account, returns ranked matches, and is a first-pass evaluation tool rather than a final answer tool. It doesn't describe pagination or exact return format, but the output schema exists and the annotations cover the safety profile, so a 4 is appropriate.

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 with zero waste. It front-loads the most important behavioral facts (FREE, no account), states the purpose, and then gives explicit usage guidance. Every sentence earns its place.

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

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

Complete for a search tool with a rich output schema, full schema coverage, and annotations covering the safety profile. The description tells the agent when to use it, what it returns (ranked matches), and what it is not for. Nothing an agent needs to call it correctly is missing.

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

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

Schema description coverage is 100%, so the schema already documents both parameters (query and limit) with descriptions, defaults, and constraints. The description adds the context that the query is a 'Bitcoin topic, concept, event, person, protocol feature, or research phrase' and that limit is the 'Maximum number of ranked knowledge matches to return', but this largely mirrors the schema. Baseline 3 is correct when the schema does the heavy lifting.

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 ('search'), a specific resource ('canonical Bitcoin Knowledge Atlas topics and related history'), and a clear purpose ('evaluate coverage on the caller's real question'). It also distinguishes itself from siblings by noting it is a no-cost evaluation tool for discovering maintained topic coverage, not a final evidence-grade answer 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 explicitly says when to use it ('Run the first no-cost evaluation when you need to see which maintained Bitcoin topics and evidence match a query') and when not to use it ('Do not use when a canonical topic id is already known or when a final evidence-grade answer is required'). It also mentions the FREE/no-account aspect, which is a clear usage condition.

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, openWorldHint, idempotentHint, and non-destructive behavior Domestication. The description adds valuable non-obvious context: the tool is free, requires no account, does not authorize payment, and is meant only for product selection. This complements rather than contradicts 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 compact and front-loaded with the most important constraint (FREE, no account). The repetition of 'FREE' is a minor redundancy, and every other sentence carries meaningful usage or behavioral guidance, so only a small deduction applies.

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

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

The tool has a single enum parameter, an output schema, and rich annotations. The description fills the remaining gaps: pricing/contract inspection, no payment authorization, and the precise moment to use it. Nothing an agent needs to call it correctly is missing.

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

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

With 100% schema_description_coverage and a well-described enum for the single required parameter, the description does not need to add much. It does restate the task enum values and frames them as research intent, but this is largely redundant with the schema's own parameter description.

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

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

The description states a specific action—'Select a research product'—and clarifies it is an inspection/selection step for price, evaluation path, and contract. It explicitly distinguishes itself from executing research or authorizing payment, which separates it from sibling research-execution tools like answer_bitcoin_question or verify_bitcoin_claim.

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 gives explicit when-to-use guidance: 'Use after free evaluation when the correct specialist product is unclear.' It also gives explicit when-not-to-use guidance: 'Do not use it to execute research or authorize payment,' and directs choosing the smallest appropriate product before paid requests.

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 annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is established. The description adds valuable behavioral context beyond these: it states the tool 'never authorizes or initiates payment' and returns a 'source-backed deterministic answer' with 'compact maintained-coverage matches.' This extra detail is useful for agent decision-making without contradicting 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 front-loaded with 'FREE' and 'START HERE,' but it contains unnecessary repetition: 'Default first call for an unfamiliar agent' appears twice, and 'FREE' is also repeated. While the content is useful, the redundancy makes it less concise than it could be. A more streamlined version would earn a higher score.

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

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

The description covers the tool's purpose, usage timing, behavioral constraints, and what it returns (source-backed answer, matches, next action). It also addresses payment concerns and directs the agent to evaluate coverage. Since an output schema exists, the lack of explicit return format details is acceptable. The only minor gap is the slight redundancy, but all essential context is present.

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

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

The schema already documents the single parameter 'query' with a clear description ('Bitcoin question or research task to answer using maintained California Bitcoin knowledge.') and provides an example. The tool description adds minimal extra parameter semantics—it only restates that it handles 'any Bitcoin question or research task,' which is already implicit in the schema. 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 clearly states this is a free entry point for any Bitcoin question or research task, returning a source-backed deterministic answer and a smallest safe next action. It distinguishes itself from siblings by explicitly labeling itself as the default first call for unfamiliar agents and the tool to use before any paid option, making its purpose and scope 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 gives explicit when-to-use instructions: 'Default first call for an unfamiliar agent,' 'Use it before any paid tool when coverage has not yet been evaluated,' and 'Do not use it to authorize payment.' It also tells the agent to evaluate coverage before choosing another tool, which is clear guidance on when to use this tool versus alternatives.

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

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

Annotations already cover read-only, idempotent, open-world, and non-destructive behavior. The description adds useful behavioral context beyond this: the tool returns a 'conservative' verdict, includes 'source-backed evidence metadata,' and is paid via 'MPP.' These details help the agent understand the operation's constraints and cost.

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

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

The description is dense but efficient: each sentence adds a distinct piece of information — cost, function, context, and exclusions. The most important operational constraint ('Use only for concrete proposition') appears clearly, and there is no redundant filler.

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

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

For a single-parameter tool with a rich output schema and strong annotations, the description is complete. It defines the input type, the adjudication scope, the verdict vocabulary, the output metadata, and the non-use cases. 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.

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

Schema coverage is 100%, so the single 'claim' parameter is fully documented in the schema. The description only reinforces that the claim must be 'one specific Bitcoin factual proposition,' which is mildly useful but does not add substantial meaning beyond the schema.

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

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

The description names a specific verb and resource: 'Evaluate one specific Bitcoin factual proposition against verdict-eligible maintained atomic claims' and specifies the exact verdict types returned. It also differentiates itself from composing broader answers or collecting general evidence, so an agent can distinguish it from the sibling tools.

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

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

The description gives explicit when-to-use context: 'The upstream agent already has a concrete factual Bitcoin claim and needs adjudication.' It also states clear exclusions: 'Do not use for open-ended explanation or general evidence collection.' It stops short of naming which sibling tool to use instead, so it is not a full 5.

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