US Brand Intelligence

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

With no annotations, the description must carry the full burden. It discloses the tool is free and that it lists items, which implies a read-only operation, but it does not explicitly state 'no side effects' or whether any authentication is needed. Adequate for a list tool but lacks explicit safety wording.

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

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

Two sentences, front-loaded with the verb 'list' and essential attributes. The first sentence states the function, the second gives usage context. No repetition or fluff; every word earns its place.

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

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

For a simple zero-parameter tool without an output schema, the description fully covers what it does, what data it returns, and when to call it. It even adds business context ('Free', 'call first') that helps the agent decide usage. No missing critical information.

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

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

The tool has zero parameters, so schema coverage is trivially 100%. The description needs to explain nothing about parameters; the baseline for 0-param tools is 4, and the description appropriately omits any parameter details.

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

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

The description uses a specific verb ('list') and identifies the exact resource ('every paid tool in the 'us-brand-intelligence' bundle') plus the data returned (price, payTo address, network). This clearly distinguishes it from sibling tools, none of which are about pricing or listings.

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 explicitly says 'Call this first if you don't have a wallet ready yet,' offering a concrete when-to-use directive. The phrase 'call this first' also implies a sequencing recommendation, and 'Free' suggests a low-risk initial step. Although no alternative tool is named, the guidance is unambiguous.

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

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

With no annotations, the description carries the transparency burden. It discloses key behavioral traits: deterministic output, absence of message sending or destination writes, and a pricing model. However, it omits that optional explanation mode may invoke an external LLM (via openrouterApiKey), which is a relevant side effect not covered elsewhere.

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

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

The description is two sentences plus cost, with no filler. The first sentence packs purpose, input, output, and output components; the second clarifies a critical behavioral boundary. Every sentence provides distinct value.

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 tool with 7 parameters and nested objects, the description captures the essence: input, processing nature (deterministic, prioritized), output traits (evidence, urgency, ownership, rule traces), and a key safety constraint. It correctly relies on the schema for parameter details, and there is no output schema to explain. A complete, high-level picture.

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% — every parameter has its own detailed description, including the XOR between items and datasetId. The tool description adds only high-level context ('verified US brand signals') and does not provide additional parameter-level meaning, so 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 uses a specific verb ('Turn') and names a concrete resource ('verified US brand signals' → 'deterministic prioritized action queue'). It clearly distinguishes from sibling tools by adding 'The Actor does not send messages or write to destinations', which positions it as a pure processing/queue-building tool, not a sender or writer.

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 clear context: it is for downstream operators and agents needing a prioritized queue. The 'does not send messages or write to destinations' clause provides an implicit when-not, but it does not explicitly name alternatives from the sibling list (e.g., webhook builder). No explicit 'use X instead' guidance.

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

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

With no annotations provided, the description carries the transparency burden and does well: it discloses non-obvious behavior—sorts facts, marks same-time groups, reports future-dated IDs, and emits stable counts/digests. It does not mention whether it verifies data, but the input schema already notes 'The Actor does not verify identity or truth', so this is adequately covered in the structured fields.

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

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

The description is two sentences: the first packs core purpose and behavioral outputs, the second adds pricing/payment metadata. Every clause contributes distinct information with no filler or repetition.

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

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

The description covers input constraints (1–30 rows, UTC as-of), core processing (sorting, grouping, future-date detection), and output categories (stable counts and digests). With no output schema present, it could detail the exact return structure more, but the high-level output description is sufficient for correct invocation.

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

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

Parameter descriptions in the schema provide 100% coverage, including asOf's explicit clock semantics, row closure constraints, and field-level patterns. The tool description adds no additional parameter-level details, so it correctly rests at the schema-covered 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 opens with 'Build a deterministic chronology from 1 to 30 closed US brand evidence rows and an explicit UTC as-of time', providing a specific verb, resource, and boundary. It then lists distinct outputs (sorting, same-time grouping, future-dated IDs, counts/digests) that separate it from sibling tools like the citation table or snapshot diff.

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 signals when to use the tool (when a deterministic chronology of closed evidence rows is needed) and is constrained to 1–30 rows with an explicit as-of time, giving clear context. However, it does not explicitly name alternatives or exclusion criteria, falling short of the 'when not to use' guidance.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states that the tool only formats supplied facts and does not verify or fetch, which is a critical trait for agent decision-making. It also hints at stability and bounded output, though it does not detail error handling or exact return format.

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

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

The description is two tight sentences: the first states the core transformation and outputs, the second adds crucial negative constraints and pricing. Every sentence earns its place, and the key information 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?

Given the tool's simplicity and the exceptionally detailed input schema, the description adequately covers the main output components. It does not describe the exact response structure, but the listed deliverables (Markdown citations, counts, limitations, digests) give a solid overview. Minor gaps exist around error handling and return format, but they are not critical for this formatting-focused tool.

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

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

Schema description coverage is 100%, with every parameter and nested property already thoroughly documented. The description only adds the qualifier 'small' to the packet, which does not materially extend parameter semantics. Baseline 3 is appropriate since 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 clearly states the tool's function: transforming a 'buyer-owned evidence packet' into a 'stable citation table' with specific output components ('bounded Markdown citations, host and source counts, limitations, and digests'). This specific verb and resource combination distinguishes it from siblings such as the chronology builder or normalizer.

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 ('small buyer-owned evidence packet') and explicit exclusions ('does not browse, fetch, verify, rank, or enrich them'), signaling it is a formatting step rather than a research tool. While it doesn't name alternatives, the 'does not' list gives strong when-not guidance.

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

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

No annotations are provided, so the description carries the burden. It discloses that the operation is deterministic, inline-only, and returns a stable machine-readable report, plus mentions pricing/payment. It does not detail error handling or exact output format, but for a pure deterministic comparison tool this is solid coverage.

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

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

The description is three tight sentences with the purpose front-loaded. Every clause adds a distinct constraint (inline-only, deterministic, buyer-supplied, cost), with zero 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?

The input schema is very rich, so input-side coverage is strong. However, there is no output schema, and the description only says 'machine-readable report' with categories; it does not specify the report's structure or how records are keyed for the diff, leaving an agent to guess at the return format.

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 baseline is 3. The tool description mostly restates high-level snapshot constraints and does not add per-parameter meaning beyond the schema; the schema already documents primarySide, required arrays, and dedupeKey uniqueness.

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 ('Compare') and resource ('two small buyer-supplied US brand evidence snapshots'), and explicitly names the output categories (added, removed, changed, unchanged). This clearly distinguishes the tool from sibling aggregation, analysis, or queue 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 the tool is 'designed for agents that already own both snapshots' and is 'Inline-only', which tells the agent when to use it and excludes external-fetch scenarios. It does not name a specific sibling alternative, so it falls 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?

With no annotations, the description carries the full burden. It discloses that the tool is 'deterministic', requires no buyer URL, API key, browser, or LLM, and costs $0.05/call. These are key behavioral traits. It does not cover error handling or rate limits, but it provides meaningful details beyond a simple API call.

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

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

The description is two sentences, front-loaded with the core purpose, followed by target audience and operational constraints. Every phrase adds value—no filler, no redundancy. The cost and external-dependency information is packed efficiently.

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 no output schema, so the description should clarify what the snapshot contains; it only says 'deterministic snapshot of federal contract transactions' which is vague. The input schema partially compensates via the maxResults description ('one snapshot row'), but error behavior and exact return fields are not covered. Adequate but with gaps for an agent deciding whether to invoke.

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 all 5 parameters. The description reinforces the main input constraints ('one exact USAspending recipient ID and a bounded UTC date window') but does not add semantics for requestId or maxResults beyond what the schema provides. 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 explicitly states: 'return a deterministic snapshot of federal contract transactions for that recipient', which clearly identifies the tool's function. It uses a specific verb ('return') and resource ('federal contract transactions'), and the tool name itself is distinct among siblings, leaving no ambiguity.

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

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

The description says 'Built for company and government-intelligence agents' and 'no buyer URL, API key, browser, or LLM', providing clear context on when this tool is appropriate (direct, deterministic data retrieval without external dependencies). It does not explicitly mention when to avoid it or name alternatives, but the context is sufficient for most agents.

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

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

With no annotations, the description carries the full burden. It discloses key behaviors: validation without browsing or inferring ownership, deterministic JSON output, and the $0.05/call pricing. It additionally implies a read-only interaction with datasets. While it does not mention error handling or rate limits, the provided information is meaningful and goes beyond a simple restatement of purpose.

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

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

The description is two sentences plus a pricing tag, front-loaded with the core purpose, followed by usage details and cost. There is no fluff; every element earns its place, making it both concise and informative.

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 complex input schema and no output schema, the description covers purpose, input methods, validation behavior, and output type (closed deterministic JSON). It stops short of detailing the exact output structure or error scenarios, but the rich schema and prefill example partially compensate. A 4 reflects that it is mostly complete for an agent to select and invoke 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 the schema already contains extensive descriptions for all parameters (e.g., rows, datasetId, options). The tool description adds no parameter-specific insight beyond what the schema provides, so it meets the baseline of 3 but does not exceed it.

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 a specific action: 'Turn supplied US brand offer, coupon, ad, and landing-page evidence into closed deterministic JSON.' This distinguishes it from sibling tools like chronology-builder or citation-table by focusing on normalization into structured JSON. It also names the evidence types and output format, making the tool's 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 provides clear context on how to use the tool: 'Submit bounded inline rows or one authorized read-only Dataset.' It also notes that the Actor validates source proof and terms, implying the tool should be used when evidence needs to be normalized and validated. However, it does not explicitly contrast with alternatives or state when not to use it, so a 4 is appropriate.

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

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

No annotations are present, so the description carries the full burden of behavioral disclosure. It clearly states 'without browsing, enrichment, inference, or child calls,' indicating no side effects, and promises 'stable groups, exact IDs, counts, and SHA-256 digests,' which describes output guarantees. The pricing note '— $0.05/call, x402 (USDC on base)' also discloses a financial behavior. Minor omissions like error handling or concurrency are not critical for this simple operation.

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 exceptionally concise: two sentences that front-load the core action, then cover output and constraints. The pricing is appended with an em-dash, adding useful information without disrupting flow. 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?

The tool is simple and the schema is rich, but the description still adds necessary context by specifying the outcome ('stable groups, exact IDs, counts, and SHA-256 digests') and limitations ('bounded batch', 'without... inference'). Since there is no output schema, this description appropriately communicates what the agent will receive. It could specify exact output structure keys, but the current text is adequate for an agent to select and invoke the tool.

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

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

Schema description coverage is 100% and every parameter has a detailed description. The tool's description only reiterates the grouping fields that are already enumerated in the schema's groupingMode enum and row properties. Thus, it adds no significant semantic value beyond the schema, aligning with the baseline 3 for high coverage.

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

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

The description opens with 'Split a bounded batch of normalized US brand signal rows by brand, event type, severity, or analysis status,' which clearly states the action (split), the resource (bounded batch of normalized rows), and the grouping dimensions. This distinguishes it from siblings like cross-tabulator or aggregator by focusing purely on partitioning without further analysis.

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 phrase 'without browsing, enrichment, inference, or child calls' explicitly sets expectations for when this tool is appropriate—pure deterministic grouping with no external side effects. While it doesn't name alternative tools, it implies use for partitioning tasks and excludes heavier processing workflows. The 'bounded batch' and 'normalized' qualifiers further clarify input constraints.

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

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

With no annotations, the description carries the full transparency burden. It discloses deterministic output, absence of live enrichment, no browsing, no source verification, and a per-call price. It does not explicitly mention whether data is modified or return value details, but the exclusions and deterministic claim strongly imply a side-effect-free computation. This is useful but not exhaustive.

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

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

The description is two sentences, with the core action and constraints front-loaded. The pricing and payment detail at the end is extra but relevant context. No wasted words; every clause adds information.

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

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

The description gives good high-level context and constraints, but because there is no output schema, the exact return format ('deterministic counts and grouped facts') is vague—grouped by what? counts of what? It does not fully specify the output structure. The input-side behavior is well-covered, but output details are insufficient for a tool without an output schema.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds meaningful constraints not fully explicit in the schema, such as the 1–60 signal range, the 15-brand limit, and the 'buyer-supplied normalized' nature of inputs. This enriches the parameter semantics beyond the schema's own field descriptions.

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

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

The description uses a specific verb ('Summarize') and clearly identifies the resource: buyer-supplied normalized US brand signals, with explicit bounds (1 to 60 signals, up to 15 brands). It also distinguishes itself from siblings through the output ('deterministic counts and grouped facts') and exclusions ('without identity resolution, source verification, browsing, or live enrichment').

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 clear context for when to use the tool (summarizing normalized buyer-supplied signals) and explicitly states what it does not do (identity resolution, source verification, browsing, live enrichment). However, it does not name specific alternative tools or provide direct comparison, so it falls short of full 'when-not/alternatives' guidance.

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

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

With no annotations, the description carries the full burden and does well: it discloses that the operation is 'bounded deterministic' and explicitly states it does not discover/fetch/verify/enrich, implying no external side effects. It does not mention details like input sorting (covered in schema), but the core behavioral traits are revealed.

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

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

The description is two sentences plus a pricing annotation. Every clause earns its place: purpose, behavioral constraints, and cost. It is front-loaded, zero waste, and highly 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?

The tool is simple, with a detailed schema covering all parameters. The description explains the output as a 'machine-readable brief' and emphasizes determinism. It lacks an explicit return format, but given the low complexity and clear purpose, the description is largely complete for agent 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 description coverage is 100%, so the parameters are already fully documented. The description adds a meta-context ('buyer-supplied snapshot') that indirectly clarifies the inputs, but it does not add any parameter-specific semantic detail beyond what the schema provides. 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 uses a specific verb ('Turn') and clearly identifies the resource and outcome: a buyer-supplied snapshot becomes a 'bounded deterministic machine-readable brief.' It also distinguishes from siblings by explicitly stating what it does NOT do (discover, fetch, verify, or enrich evidence), which separates it from related 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 implies the intended use case: you provide the snapshot, and it reduces it. The negative constraints ('does not discover, fetch, verify, or enrich evidence') signal when not to use this tool, but it does not explicitly name alternative tools or provide a when/where-not-to-use structure. Still, the context is clear.

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

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

With no annotations provided, the description carries the full burden. It discloses the output structure (sorted IDs, reason codes, counts, digests), states 'no source or identity claims are made,' and even includes cost/pricing details. It doesn't explicitly state side effects, but as a classification tool, the behavioral profile is well conveyed.

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

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

The description is two sentences plus a pricing note. Each sentence earns its place: first states the core action and resource, second details the output and key limitation, third provides cost information. No redundancy or fluff.

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

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

The tool has no output schema, but the description enumerates the key output components. The input schema is highly detailed, and the description adds relevant constraints (buyer-supplied, no verification, no source claims). It lacks explicit edge-case handling, but for a threshold-based classifier, the description is adequately complete.

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

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

The schema covers all parameters thoroughly, so the baseline is 3. The description adds meaning by tying parameters to the classification outcome and noting 'buyer-supplied' and 'no source or identity claims,' but it does not elaborate on parameter syntax beyond what the schema already provides.

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 ('Classify') and resource ('buyer-supplied normalized US brand signal scores') against explicit thresholds, and clearly distinguishes itself by detailing the accept/review/reject output. The sibling tools are all signal-related, but none explicitly classify against accept and review thresholds like this one.

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 you have normalized signal scores and want to classify them, but it does not explicitly mention when not to use it or name alternative sibling tools. The pricing note adds context but not usage guidance.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states that the tool does not fetch data, does not draw causality conclusions, and provides deterministic-looking 'stable' outputs. It also mentions pricing and payment method, which is an unusual transparency bonus. However, it does not describe mutation side effects (it's clearly read-only but not explicitly stated) or data handling policies, though the risk is low for a pure analysis 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 highly concise: two sentences, the first stating the core purpose and the second enumerating outputs and constraints. It is front-loaded with the most important information, and every clause earns its place. Pricing is included without diluting the message.

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's enumeration of outputs (signal counts, pair counts, support, Jaccard overlap, digests) provides a good sense of what the tool returns. It also mentions constraints like bounded groups and no fetching, and the differentiation from siblings helps selection. It lacks details on output format, error handling, or pagination, but for a small co-occurrence analyzer, it is sufficiently complete.

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

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

Schema coverage is 100%, so the schema already fully documents the parameters. The description adds valuable context about what buyer-supplied groups mean and what the tool computes from them, but it does not add per-parameter information beyond the schema. This aligns with the baseline of 3 for high schema coverage.

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

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

The description uses a specific verb ('Measure') and clearly identifies the resource and scope ('how often buyer-supplied opaque signal IDs appear together in bounded observation groups'). It also lists concrete outputs (signal counts, pair counts, support, Jaccard overlap, digests) and explicitly differentiates from sibling tools by stating 'without fetching or making causality claims'.

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 the tool (when you have observation groups and want co-occurrence statistics) and sets boundary conditions, but it does not explicitly name alternatives or provide exclusions. There is no direct comparison to sibling tools like us-brand-signal-cross-tabulator or us-brand-signal-metrics-aggregator, so guidance is present but implicit rather than explicit.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It clearly states that no network calls, credentials, or LLM operations occur, and that evidence IDs/URLs are preserved, which is valuable context. It does not describe the exact return format or error behavior, but the 'unsent field proposals' phrasing gives a reasonable expectation of the output.

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

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

The description is concise and front-loaded: the first clause states purpose, the second lists key constraints, and the third provides pricing. No words are wasted, and each segment serves a distinct role, making it easy to parse quickly.

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

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

For a tool with a highly detailed schema and no output schema, the description covers the critical operational context: row limits, target CRMs, non-connectivity, and pricing. It could be more complete by briefly describing the shape of the returned proposal, but given the schema richness, this is a minor gap.

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 fully documents all parameters and nested properties. The description adds minimal extra parameter semantics beyond reiterating row count and target CRMs, which are already in the schema. It meets the baseline without compensating gaps.

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

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

The description clearly states the tool's function: converting 1 to 100 buyer-supplied US brand signal rows into unsent CRM field proposals for HubSpot, Salesforce, or generic CRM, while preserving evidence IDs and URLs. It uses a specific verb ('Turn... into') and resource ('US brand signal rows'), making it distinct from siblings like the webhook payload builder.

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 explicit exclusions ('No CRM credentials, network calls, proxy, LLM, identity resolution, or arbitrary expressions') that clarify when not to use the tool, and specifies it produces 'unsent' proposals. However, it does not explicitly name alternative tools for cases where sending or enrichment is needed, so it lacks full alternative guidance.

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

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

With no annotations, the description carries the burden and does well by disclosing 'deterministic', 'only counts the bounded request', 'does not verify sources or infer causality', and pricing. It does not mention error handling or exact return structure, but the core behavioral boundaries are clearly stated.

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, efficiently worded sentence followed by pricing. It front-loads the core purpose and boundaries without redundant jargon, making every part 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?

The tool is simple, schema-rich, and the description covers purpose, input nature, and non-goals. Although there is no output schema, the phrase 'count table' implies the output. Sibling differentiation is adequate with the 'does not infer causality' caveat. Minor gap is lack of explicit output format, but overall it is sufficiently complete.

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

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

The schema description coverage is 100%, with the schema already defining rows, rowId, rowDimension, columnDimension, and schemaVersion. The description provides examples that map conceptually to row/column dimensions but adds no syntactic detail beyond what the schema offers, 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 uses a specific verb ('Build') and a clear resource ('two-dimensional count table'), with concrete examples ('event type by status or brand by review state'). It also differentiates from siblings by emphasizing 'deterministic' and 'buyer-supplied opaque rows' without external source retrieval.

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 provides clear context for when to use the tool: for counting bounded, buyer-supplied rows in a cross-tabular format. It also states exclusions ('does not verify sources or infer causality'), which helps distinguish from analysis tools like cooccurrence-analyzer or metrics-aggregator, though no explicit alternative tool is named.

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

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

With no annotations, the description carries the full burden and does well: it discloses determinism, the absence of winner selection, the list of report components, and even pricing/payment ('$0.05/call, x402 (USDC on base)'). It does not mention error behavior or whether the operation is side-effect-free, but the tone implies a pure computation.

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

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

Two sentences deliver high density of information: purpose, output categories, constraints, and pricing. No filler, no redundancy, and the most important details are front-loaded.

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

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

Given no output schema and no annotations, the description provides a helpful list of report contents (union, duplicates, conflicts, one-sided sets, counts, digests). Input validation is fully covered by the schema. It lacks exact return structure and error handling, but is complete enough for tool selection and basic 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?

The input schema covers 100% of parameter descriptions, so the baseline is 3. The description adds general context about the left/right batches but does not add per-parameter meaning beyond the schema; the schema already explains the structure and constraints of each input.

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

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

The description clearly states the tool's purpose with a specific verb ('Reconcile') and resource ('two buyer-supplied batches of normalized US brand signals'). It enumerates the exact outputs (deterministic union, duplicate IDs, field conflicts, one-sided ID sets, counts, digests) and explicitly distinguishes its non-goal ('without choosing a winner'), setting it apart from 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 implies the use case: when you need to compare two batches and generate a merge report without adjudication. The phrase 'without choosing a winner or making a truth claim' serves as a clear exclusion, but it does not explicitly name alternative tools or provide when-not-to-use scenarios, so it stops 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?

With no annotations, the description carries the full burden and excels: it discloses statelessness, keyless operation, offline processing, bounded input, determinism, and even per-call cost. This gives the agent a complete safety and execution profile without needing annotations.

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

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

Two concise sentences: the first front-loads the verb and object, the second packs constraints and pricing. No filler or redundant restatement, every word contributes.

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 two-parameter tool with fully documented schema, the description adds key contextual details like offline/stateless operation and cost. It does not describe the output format, but no output schema exists and the metric list implies the output shape, making it nearly complete.

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

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

Schema description coverage is 100% for both parameters, so the baseline is 3. The description adds high-level context (what the metrics aggregate) but does not introduce any parameter-level semantics beyond what the schema already provides, which is adequate but not additive.

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 a specific verb ('Compute') and resource ('deterministic machine-friendly metrics for US brand signal rows'), and lists the metric categories (event, severity, status, source, confidence, warning, digest). This distinguishes it from sibling tools like the batch splitter or confidence gate, which have different purposes.

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 clear usage context: it operates on rows 'you already collected' and is designed for agent pipelines with stateless/offline/bounded behavior. However, it does not explicitly name alternative tools or state when not to use it, falling just short of full exclusion guidance.

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

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

No annotations are provided, so the description carries the full burden. It discloses key behavioral aspects: the tool returns categorized IDs, differences, and sensitivity summaries, and it does not select a policy. It also reveals the cost ($0.05/call, x402 USDC), which is useful operational context. However, it does not explicitly confirm read-only behavior or mention any side effects, though comparison strongly implies non-mutating.

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

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

The description is two sentences long, front-loaded with the primary action, then detailing outputs and a key non-behavior, followed by cost/payment info. Every phrase adds value, with no redundant or filler content. It is efficiently structured and easy to scan.

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

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

Given the tool's moderate complexity, rich input schema, and absence of an output schema, the description covers the essential context: purpose, inputs (via schema), outputs (accepted/review/rejected IDs, differences, sensitivity summaries), and the important caveat that no policy is chosen. The cost note is a bonus. It could be more specific about what 'sensitivity summaries' contain, but this is sufficient for tool selection and basic 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?

The input schema already provides 100% coverage with detailed descriptions for all parameters: row IDs, score ranges, threshold semantics, and the ordering constraint. The description adds marginal context like 'buyer-defined' and 'opaque' but these are also reflected in the schema. Thus, the schema does the heavy lifting, and the description does not need to add much more, earning the baseline 3.

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

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

The description clearly states the tool's function with a specific verb ('Compare') and resource ('buyer-defined threshold policies') over 'opaque US brand signal scores'. It also lists concrete outputs (accepted/review/rejected IDs, differences, sensitivity summaries) and distinguishes itself by explicitly noting it does not choose or recommend a policy, which differentiates it from many sibling signal 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 implies when to use this tool: when comparing multiple threshold policies against the same signal scores. It also provides an exclusion by stating it does not recommend or choose a policy, signaling that a different tool should be used for recommendation. However, it does not name specific alternative tools, so it stops short of fully explicit guidance.

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

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

Since no annotations are provided, the description carries the full burden. It transparently discloses deterministic behavior, non-mutating nature (no sending/calling/fetching), and that it does not infer identity. It also adds context such as the cost ($0.05/call) and reproducibility, going beyond the name to set accurate expectations.

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

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

The description is extremely concise: two sentences that front-load the core transformation and outputs, followed by explicit non-behaviors and cost. Every clause carries information, with no repetition or fluff.

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

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

Combined with the exhaustively detailed input schema, the description adequately covers inputs, constraints, and non-effects. Although there is no output schema, the description summarizes the return elements (matched routes, unmatched IDs, counts, warnings, digests). It does not specify exact digest formats, but that level of detail is not necessary for correct invocation.

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

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

The input schema provides 100% description coverage for all four parameters, with detailed constraints, defaults, and runtime notes. The tool description adds only high-level framing (e.g., 'normalized US brand signals' and 'ordered rules') but no additional parameter-specific meaning. Given the schema's thoroughness, a 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 clearly states the tool's purpose: turning normalized US brand signals and ordered rules into a deterministic routing plan with concrete outputs (matched routes, unmatched IDs, counts, warnings, reproducible digests). It also explicitly distinguishes itself by listing what it never does (sends messages, calls destinations, fetches URLs, infers identity), setting it apart from sibling tools like webhook builders or action queues.

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 that the tool is for planning/routing only and explicitly lists non-actions, effectively telling the agent what not to use it for. However, it does not name alternative tools or provide explicit 'when to use this vs. that' guidance, so it falls 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?

With no annotations, the description carries the burden. It discloses that the tool is a bounded processor (only analyzes the JSON you provide) and makes no identity or causality claim, which is useful context. However, it omits return shape, possible side effects, or rate limits, leaving some gaps in behavioral disclosure.

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

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

Two concise sentences, front-loaded with the primary verb and resource, followed by pricing and caveats. Every clause adds information without redundancy, making it easy to parse quickly.

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

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

The description explains what the tool does and its constraints, and the schema covers inputs well. However, there is no output schema or description of the return value, which is a significant omission for an analysis tool. The pricing and x402 note are useful but not essential to invoking 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?

The input schema already describes both parameters fully (100% coverage), including patterns and descriptions for sequenceId and stepIds. The description adds little beyond framing sequences as 'opaque' and focusing on adjacent transitions, meeting the baseline for schema-heavy parameter documentation.

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

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

The description clearly states the tool's function: measuring ordered adjacent transitions in buyer-supplied opaque sequences, with explicit use cases for workflow, funnel, and journey analysis. This specific verb+resource combination distinguishes it from siblings like cooccurrence-analyzer or cross-tabulator, which analyze different aspects of the sequences.

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 provides clear context for when to use the tool—when you have ordered sequences and need transition analysis—and specifying that it only processes the provided JSON. However, it does not explicitly exclude alternatives or name sibling tools, stopping short of a full 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states the tool is deterministic, offline, never fetches a clock, and never performs identity resolution. This goes beyond the schema's parameter descriptions and provides essential trust-related information. No contradictions with annotations exist.

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

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

The description is extremely concise—two sentences plus a pricing note—and every element earns its place. The first sentence defines the core purpose, the second adds key behavioral constraints, and the pricing information is practical. It is well-structured and immediately front-loaded with the most critical information.

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

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

Given the tool's moderate complexity and the absence of an output schema, the description adequately explains what the tool returns by naming the three classification categories (met, missed, open). It also covers the crucial constraints (offline, no clock, no identity resolution) and the parameter semantics are fully handled by the schema. The description is complete enough for an agent to select and invoke 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%, with each parameter (asOf, rows, schemaVersion) already well-documented. The description adds minimal parameter-specific detail beyond what the schema provides, though it does reinforce that 'asOf' is an explicit UTC timestamp and that item IDs are opaque. This meets the baseline of 3 but does not significantly exceed it.

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

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

The description clearly states the tool's function: 'Classify buyer-supplied schedule rows against an explicit UTC timestamp: which items met their due time, missed it, or remain open.' This specifies the action (classify), the resource (schedule rows), and the exact output categories, distinguishing it from any sibling tools. It is not a tautology and adds meaningful detail.

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 clear context for when to use the tool—when you need deterministic, offline classification of rows against a provided timestamp. It explicitly notes it 'never fetches a clock or resolves an item to a person or company,' which clarifies limitations. However, it does not mention alternative tools or explicitly state when not to use it, so it stops 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?

With no annotations, the description carries the full burden, and it does a good job: it discloses the tool is deterministic, bounded, unsent, and never sends a webhook or accepts a destination, and it also notes the $0.05/call cost. It does not mention other behavioral traits like 'no live-source lookup' or 'pages not fetched,' but those are covered in the input schema, and the core safety guarantee is clearly stated.

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

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

The description is two sentences, front-loaded with the primary purpose and followed by a crucial constraint and pricing note. Every word adds value: 'bounded deterministic,' 'unsent,' 'never sends,' and the cost/call details. There is 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?

The description adequately explains the tool's scope for a payload builder: it names the target formats, clarifies the unsent/destination-free behavior, and mentions the bounded deterministic output. The lack of an output schema is partially mitigated by the description's phrase 'payload shaped for...' which implies a returned payload, but a bit more detail about the return value would make it fully complete.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds minimal additional meaning beyond 'one normalized signal and buyer-supplied evidence' and the named target formats, but the heavy lifting is done by the detailed schema descriptions. This meets the baseline but does not exceed it.

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 ('Build') and a clear resource ('one bounded deterministic unsent payload shaped for Slack, Teams, or a generic webhook'), immediately distinguishing this tool from sibling tools. It also clarifies the inputs ('one normalized signal and buyer-supplied evidence') and even states what it does not do ('never sends a webhook or accepts a destination').

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 a clear context: this tool is for constructing an unsent, destination-free payload rather than performing any transmission. It explicitly rules out sending and accepting a destination, which helps an agent choose it over a sending tool. However, it does not name sibling alternatives or give explicit 'use when' versus 'use instead' guidance, so it misses the top score.

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