MARS Economic

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

No annotations exist, so the description carries the full behavioral burden. It does disclose real traits beyond the schema — buyer deduplication, capability verification of suppliers, sequential external-source execution, targeted supplier recovery, and a deployment gate — which is meaningful context. But it omits permissions, rate limits, side effects, and reversibility, and the dense phrasing leaves the actual behavior ambiguous.

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?

It is a single front-loaded sentence with the purpose first, which is good structure. But it crams seven dense, comma-jammed clauses into one run-on line without prioritization, making it hard to parse which traits matter most.

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 three-parameter orchestration tool with no annotations, no output schema, and 0% parameter documentation, the description is too thin. It gestures at internal behaviors but leaves the agent without the parameter guidance or prerequisite/permission details needed to invoke it correctly.

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

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

Schema coverage is 0% and none of the three parameters (limit, queries, buyer_limit) are explained in the description or schema. The phrase 'across multiple buyer-demand families' loosely suggests the queries parameter and the 'ranked' wording loosely suggests limit/buyer_limit, but no syntax, format, or meaning is given, so the description fails to compensate for the coverage gap.

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?

It states a specific verb ('Build') and resource ('ranked portfolio across multiple buyer-demand families'), so the core purpose is inferable. However, the term 'economic opportunity portfolio' is jargon-heavy and the description gives no hint about how it differs from siblings like build_portfolio_conversion_queue or discover_buyer_demand, which share the same vocabulary.

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?

There is no explicit when-to-use guidance and no named alternative. An agent cannot tell from this text when to prefer this tool over build_portfolio_conversion_queue or discover_buyer_demand, nor what preconditions must hold. The clause 'no named-counterparty deployment gate' hints at a policy but is not framed as 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, and it does disclose real behavioral traits: deduplication, deadline prioritization, owner-approval gating, and the important guarantee that nothing is sent automatically. However, it omits permissions required, whether it mutates persistent state, and what the queue returns.

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 core action and resource, then the behavioral guarantees. Efficient, though the first sentence is a heavy noun stack that costs some readability.

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 queue-building workflow with no annotations, no output schema, and 0% parameter documentation, the description is too thin. It says what the queue is but not how to drive it, what it returns, or how it differs operationally from sibling preparation tools.

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

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

Schema coverage is 0% and the description never mentions limit, queries, or buyer_limit. For three entirely undocumented parameters, the description provides no compensating meaning, leaving the agent to guess the format and effect of each.

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?

States a specific verb (build) and a specific compound resource (portfolio-wide public business-contact enrichment and formal-eligibility outreach queue). It distinguishes itself from single-outreach siblings like prepare_formal_eligibility_outreach by scope (portfolio-wide queue), though the dense jargon makes the boundary implicit rather than explicit.

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

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

No when-to-use guidance and no named alternatives. It is unclear when an agent should call this queue-builder versus prepare_formal_eligibility_outreach, prepare_supplier_eligibility_request, or build_economic_opportunity_portfolio, all of which live in the same family.

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 does usefully disclose that no contact occurs and no money moves, effectively signaling a safe read operation, but says nothing about pagination, result volume, freshness, or rate limits.

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 front-loaded sentences with no filler; the purpose leads and the safety boundary follows. Appropriately sized, though it spends a clause on an implicit boundary rather than parameter guidance.

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

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

For a no-output-schema discovery tool, the description covers what it returns at a high level and the absence of side effects, but omits parameter semantics and any notion of result shape, leaving real gaps for the agent.

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

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

Both parameters (limit, query) have 0% schema description coverage, and the description explains neither the query syntax nor the limit's default/range. With 2 undocumented params, the description fails to compensate for the coverage gap.

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?

States a specific verb (Discover) and resource (live open Buyer demand from official procurement sources), which is clearer than a generic 'search'. It does distinguish itself in kind from siblings like discover_commercial_counterparties, but never names or contrasts an alternative explicitly.

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?

There is no statement of when to use this versus discover_commercial_counterparties or publish_demand, and no prerequisites. The 'no automatic contact and no money movement' line is a boundary, 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 behavioral burden and does contribute one meaningful trait: 'Never contacts them automatically' clarifies it is a passive discovery action. However, it does not disclose return behavior, network/data-source behavior, or any limitations, so transparency is partial.

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 short sentences with no filler: the first states the domain and the second adds a critical boundary. The structure is front-loaded and 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?

There is no output schema, so the description should indicate what a successful discovery returns, but it does not. It also omits parameter semantics and any success/error behavior, leaving an agent to guess at the result shape for a 2-parameter tool.

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

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

Schema description coverage is 0%, and the description does not explain 'query' or 'limit' or the loose additionalProperties. The property names are self-explanatory enough to avoid a 1, but the description adds no parameter-level meaning.

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 clear action and object: 'Discover commercial public A2A/MCP services and B2B SaaS commission programs.' This distinguishes the tool's domain from the broad sibling list, though it does not explicitly compare with find_counterparty.

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?

There is no guidance on when to prefer this tool over siblings such as find_counterparty or the various commercial_intelligence offers. The second sentence only states a boundary ('Never contacts them automatically'), not a usage context or alternative.

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 of behavioral disclosure. It implies a search/read operation but does not explicitly state read-only behavior, absence of side effects, rate limits, or any other operational traits. The description adds no behavioral context beyond the generic verb 'search'.

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 short sentence, but it is under-specified rather than appropriately concise. It lacks structure or front-loading of critical information; the sentence is so vague that it provides little value, making it closer to a placeholder than a useful definition.

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 three undocumented parameters, no output schema, and no annotations, the description is grossly inadequate. An agent cannot determine what arguments to pass, what the response will look like, or any constraints, making the tool effectively unusable based solely on this description.

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 0%, and the description does not mention any of the three parameters (limit, query, item_type). An agent has no guidance on what these parameters mean, their format, or how they influence the search results, failing entirely to compensate for the schema's lack of 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 states a verb 'search' and a resource 'reviewed public demand or offers', but 'reviewed' is ambiguous and the resource doesn't clearly map to the tool name 'find_counterparty'. It does not differentiate from sibling tools like discover_commercial_counterparties, making the purpose unclear and only weakly indicative of what the tool actually does.

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?

There is no guidance on when to use this tool versus alternatives. Sibling tools such as publish_demand, publish_offer, and discover_commercial_counterparties exist for related operations, but the description provides no conditions, exclusions, or scenarios for choosing this tool.

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 disclose one genuinely important behavior: the receipt/result does not verify sender identity, authenticity, or eligibility, and review is 'fail-closed'. That is valuable trust context, but nothing is said about mutation effects, persistence, idempotency, or auth requirements for the call itself.

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, action first, caveat second — front-loaded and free of filler. The dense domain jargon ('fail-closed formal review') costs a little clarity but nothing is wasted.

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?

A four-parameter, nested-object tool with no annotations, no output schema, and 0% schema coverage gets a very thin description. The safety caveat is useful, but an agent is left without enough to know what to pass in or what to expect back.

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

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

All four parameters (match, request, evidence, response) have 0% schema coverage and nested objects, so the description must compensate. It loosely gestures at 'response', 'request', and 'evidence' in prose but adds no structure, format, or expected-shape detail for any parameter.

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

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

Names specific operations (correlate a supplier response, map evidence, run formal review) against a concrete resource, so the tool's function is legible. It is distinguishable from prepare-side siblings like prepare_supplier_eligibility_request, though it never names an alternative explicitly.

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 'a supplier response with a prepared request' implies the calling context, but there is no explicit when-to-use, no sequencing guidance relative to siblings (e.g. intake_supplier_formal_eligibility), and no prerequisites stated.

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 disclose two meaningful behavioral constraints: it never self-approves authenticity or eligibility and never sends contact. However, it does not state permission requirements, what happens to unmatched or partial evidence, or any return behavior, leaving substantial behavioral gaps.

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 tight sentences with the primary action front-loaded and the safety limits following. Every clause carries meaning, though a small amount more guidance could be justified given the schema's opacity.

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 two undocumented nested-object parameters, no annotations, and no output schema, the description explains intent and boundaries but leaves the agent without any information on how to populate match/evidence or what a successful intake yields. It is insufficient to call the tool confidently.

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 0% and both parameters (match, evidence) are undocumented nested objects. The description alludes to 'formal document evidence' and 'procurement requirements', which loosely hints at the two inputs, but it provides no structure, expected shape, or format for either, failing to compensate for the coverage gap.

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?

States a specific action (map) with both the input (supplier-provided formal document evidence) and the output target (procurement requirements), which is enough for an agent to distinguish it from verification tools like verify_supplier_public_evidence. It stops short of explicitly naming the sibling it contrasts with, so it is clear but not fully differentiated.

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

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

No statement of when this tool should be invoked versus the many sibling preparation/verification tools, and no prerequisites or ordering guidance (e.g., must evidence be collected first). The scope is only implied by the word 'intake'.

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

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

Annotations already declare readOnlyHint and destructiveHint false. The description adds that it never performs payment or contact, reinforcing the safety, but doesn't disclose other behaviors like rate limits or data freshness. No contradiction.

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

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

Two sentences, concise and front-loaded with the key point. The qualifier 'FREE read-only' at the start is useful, and the negative guarantee is short. No 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?

With 3 parameters at 0% coverage and no output schema, the description is insufficient. It doesn't explain what each parameter does or what the returned data looks like, so an agent would struggle to configure calls 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 0%, so the description must compensate. It mentions 'tiers' and 'policy invariants' which hint at the 'tier' parameter, but doesn't explain 'q' or 'budgetMicros'. The parameters remain largely unexplained, making it hard to know what to pass.

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 it returns canonical Commerce V3, x402 rail, tiers, and policy invariants, providing a clear resource and purpose. It distinguishes itself by mentioning it is a handshake, but it doesn't explicitly differentiate from siblings like mars_commerce_quote or discover_commercial_counterparties.

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 it's a free read-only handshake, but it doesn't explicitly state when to use this tool versus alternatives. It mentions it never performs payment or contact, which rules out some use cases, but lacks explicit when-to-use or 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it is free, it returns alternatives and a paid execution URL, and it does not perform payment. This goes beyond the annotations by clarifying the tool's role in a multi-step commercial flow.

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

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

Two sentences with zero waste. The first sentence front-loads the purpose and outputs; the second sentence clarifies a critical boundary (no payment). 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 read-only quote tool with no output schema, the description covers the main purpose, outputs, and the key boundary (no payment). It lacks parameter-level detail for three optional parameters, but those are optional and the core behavior is well-specified. The absence of an output schema is partially mitigated by listing the return contents (value contract, price, alternatives, URL).

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 0%, so the description must compensate. It explains the core parameter 'task' implicitly ('Describe the commercial task'), but does not explain journeyId, desiredResults, or maxBudgetMicros. The description adds some meaning for the main parameter but leaves the other three parameters' semantics entirely to the schema, which has no descriptions. Baseline 3 is appropriate because the description partially compensates but not fully.

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 ('resolver'), the resource ('task-to-price'), and the exact outputs (value contract, price, alternatives, paid execution URL). It also explicitly distinguishes itself from payment tools by stating 'No payment is performed by this tool.' This clearly differentiates it from siblings like request_quote and mars_commerce_recover.

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 indicates when to use it: when you have a commercial task and need a price quote. It also explicitly states what it does NOT do ('No payment is performed'), which helps an agent avoid using it for payment execution. However, it doesn't explicitly name alternative tools or exclusion conditions, though the sibling list provides context.

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

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

The description adds behavioral context beyond the annotations: it is free, uses buyer budget, and never performs payment. These details align with the readOnlyHint and are not visible in the schema. It does not contradict 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 that front-load the core purpose and then add key behavioral constraints. Every sentence adds value and there is no redundancy.

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

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

Given five parameters and no output schema, the description is too sparse to allow correct invocation beyond knowing the trigger reasons. It does not clarify what recovery returns, how desiredResults relates to output, or how journeyId/task should be populated, leaving significant gaps.

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

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

With 0% schema description coverage, the description must compensate for parameter meaning, but it only hints at the budget parameter ('uses buyer budget when provided'). It does not explain reasonCode, task, journeyId, or desiredResults, leaving most parameters under-specified.

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 purpose: recovery after structured feedback reasons like TOO_EXPENSIVE or PAYMENT_UNSUPPORTED. It distinguishes itself from siblings by emphasizing that it is free and never performs payment, but it does not fully specify what 'recovery' produces (e.g., a new quote or retry plan).

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 when-to-use context: after certain feedback reasons. It also provides a key usage detail—'uses buyer budget when provided'—and an explicit exclusion: 'never performs payment.' However, it does not name alternative sibling tools or explicitly state when not to use 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 establish read-only, idempotent, and non-destructive behavior. The description adds meaningful context beyond those annotations: it is evidence-only, separates evidence sources, exposes non-test usage counts, and explicitly excludes synthetic scores. This helps an agent understand what kind of data it will receive.

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

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

The description is a single dense sentence that front-loads the key identity ('FREE evidence-only reliability view') and then packs the distinguishing behavioral details into a compact clause. Every phrase 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 zero-parameter, read-only evidence tool with strong annotations, the description gives enough context for an agent to select and invoke it. It does not describe the exact output shape, but there is no output schema and the description conveys the core content of the view.

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

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

The tool has zero parameters and schema coverage is 100%, so there is no parameter-semantic gap to fill. The description does not need to explain parameters, and it does not introduce any ambiguity about inputs.

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 purpose: an evidence-only reliability view that separates external settlement evidence from controlled/unattributed evidence and exposes non-test usage counts without synthetic scores. This clearly distinguishes it from scoring or quote-oriented siblings, though it uses nouns like 'view' rather than an explicit verb such as 'get' or 'retrieve'.

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 'FREE evidence-only reliability view' implies it is for callers needing raw evidence rather than synthetic scores, but there is no explicit when-to-use/when-not-to-use guidance and no named alternative. Sibling differentiation is left mostly to inference.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the bar is lower. The description adds valuable non-behavior disclosure — it will not accept jobs, contact counterparties, execute providers, broadcast transactions, or move money — which clarifies the tool is purely evaluative and non-committal, and the 'FREE' note sets cost expectations. No contradiction with annotations; the description reinforces them.

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

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

Two sentences with the key value proposition ('FREE first-stop routing precheck') front-loaded. The negative list is slightly long but each item adds distinct scope information, earning its place. Nothing extraneous or repetitive enough to warrant a 3.

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 7 optional parameters, no output schema, and no parameter descriptions, the description explains the tool's role well but omits what the agent should expect in return — a verdict, a routing recommendation, a score? Since no output schema exists, the description carries the burden of hinting at the return shape and fails to do so. It is adequate for routing intent but not 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 0%, so the description carries the full burden of explaining the 7 parameters, but it mentions none of them. While names like title, budget, and currency are self-explanatory, requiredCapabilities (an array of up to 20 strings) is ambiguous and could mean skills, certifications, or provider capabilities. The description fails to compensate for the complete lack of schema-level 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 uses specific verbs ('evaluates,' 'routes') and names the resource ('deal'), clearly stating it is a first-stop precheck that determines preliminary fit and routing. It also explicitly lists what it does not do, which distinguishes it from siblings like mars_commerce_quote, publish_demand, and record_commission_event without needing to open any 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?

The phrase 'Send a deal to MARS first' gives explicit temporal placement in the workflow, and the negative list ('does not accept jobs, contact counterparties, execute providers...') implicitly tells the agent this tool is for evaluation only, not execution. However, it never names alternative tools or states 'use X instead when Y,' so the routing guidance is implied 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?

Annotations already cover read-only/idempotent/open-world safety; the description adds that exactly one evidence-bearing result is returned, that the source is public supplier/procurement data, and that the response contains a continuation instruction to the paid x402 service. It also explicitly clarifies no payment is taken, which is beyond what the annotations state.

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 short sentences front-load the free/single-result nature and then state the paid continuation; every phrase earns its place. 'No payment is required' reinforces 'FREE' without being wasteful given payment concerns.

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 low-complexity, one-parameter, read-only tool, the description covers what the agent needs: what is returned (one evidence-bearing result), how it connects to the paid service (continuation), and cost (none). It is slightly vague about the format of the 'exact continuation' and does not describe output structure, but the annotations and schema cover the rest.

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 parameter q is fully documented in the schema ('Commercial need, product, service, supplier category, or procurement topic'), so the description adds little beyond that. The description's mention of 'supplier/procurement discovery' loosely reinforces q's purpose but introduces no new semantics.

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 concrete action ('return one evidence-bearing public supplier/procurement discovery result'), specifies the exact scope (single result, public, supplier/procurement), and contrasts with the paid x402 service. An agent can distinguish this free preview tool from the paid offer siblings.

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 makes the free/paid relationship clear ('FREE,' 'No payment required,' 'exact continuation to the 0.05 USDC... service'), implying it is the entry point before the paid service. However, it never explicitly states when to prefer this over siblings such as mars_x402_commercial_intelligence_offer or find_counterparty, nor gives exclusions.

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

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

Annotations cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), and the description adds valuable non-obvious context: the exact price (0.005 USDC), the network (Base Mainnet), the x402 v2 protocol, the payment meta-key required for retry, and the payment-response meta returned after settlement. It does not cover failure/refund behavior when settlement fails, which keeps it from a 5.

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

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

Three sentences, front-loaded with the value proposition before the payment mechanics. Dense but every sentence carries distinct information (what it returns, no account needed, how to pay/retry). Minor use of protocol jargon that could be tightened.

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 fills the gap by naming the return payload (1+ verified counterparty with public evidence, compact decision summary, payment-response meta). For a two-parameter read tool with full annotation coverage, this is close to complete; the only missing piece is error/refund handling.

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 both parameters (q, journeyId) are already documented in the schema. The description adds no format, length, or example detail beyond the schema baseline, so the standard 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?

States a specific verb+resource: 'one-call paid procurement evidence' for supplier sourcing, vendor discovery, and counterparty research. This is clearly distinguishable from the free-preview and commerce-quote siblings by the 'paid evidence' framing, though no sibling is named explicitly.

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 walks through the x402 invocation sequence (first call returns PaymentRequired, retry the SAME call with payment), which is genuinely useful procedural guidance. However, it never states when to prefer this paid offer over siblings like mars_free_commercial_intelligence_preview or discover_commercial_counterparties, leaving the routing decision implicit.

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 a useful privacy guarantee: no free text, IP, User-Agent, referrer, or raw journey id is stored. This partially compensates for the all-false annotations. But it doesn't disclose what feedback is stored, whether the call returns anything, or whether repeated calls are safe.

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 short sentences lead with the tool's optional, reason-coded nature and put the privacy guarantee second. There is no filler or repetition, and the description is 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?

For a tool with 8 parameters and no output schema, this description is too thin: it doesn't state the intended purchase-flow trigger, what the response means, or how the reason code relates to downstream behavior. The privacy note is helpful but does not make the tool safely callable.

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 0% schema description coverage, the description should explain key parameters, but it only hints that reasonCode is central and that task/journeyId are not retained. Fields like retryIntent, paymentCapability, and expectedMaxPriceMicros are left entirely to the schema, so the description adds minimal semantic value.

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

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

The title and first sentence establish that this tool collects anonymous purchase feedback using a reason code, and 'FREE optional' adds useful framing. However, it lacks an explicit verb like 'submit' or 'record' and does not contrast with sibling feedback/attribution tools, so it is clear but not sharply differentiated.

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 only says the feedback is 'optional' and gives no condition for when to call it, such as after a declined offer or failed payment. No alternative tools are mentioned and no exclusions are given, so an agent would have to infer the trigger context from the name and schema.

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 aligns with the readOnlyHint and goes beyond annotations by specifying that no payment is required, the exact data returned, and the follow-up action to purchase. It adds concrete behavioral context (returns specific fields, triggers a purchase only if the agent chooses to call the endpoint) without contradicting any annotation.

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

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

The description is two sentences with zero redundancy. The purpose is front-loaded in the first sentence, and the second sentence gives a clear call-to-action for purchase. Every word contributes meaning.

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

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

For a parameterless tool with no output schema, the description fully covers what the tool does, what it returns, and the next step to buy. No critical information is missing for an agent to decide whether to invoke it and what to expect from the response.

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 parameter semantics are trivially satisfied. The description conveys the fixed nature of the offer (endpoint, price, network) without needing parameter documentation, meeting the baseline for a parameterless tool.

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

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

The description uses a specific verb 'Inspect' with a specific resource 'exact paid-service offer' and enumerates the exact return fields (endpoint, price, network, asset, receiver). It clearly distinguishes this inspection tool from a purchasing action and provides enough specificity that an agent can understand what it does without opening 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?

The description implies usage as a pre-purchase inspection step by saying 'without paying' and then directing the agent to call the returned endpoint to buy. However, it does not explicitly differentiate from sibling tools like mars_free_commercial_intelligence_preview or mars_micro_commercial_intelligence_offer, nor does it state when not to use this tool. Guidance is implied 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, the description carries the full burden, and it does add two real behavioral facts: it never contacts parties or moves money, and it enforces a signed-mandate gate. However, it does not say whether the tool is read-only or persists matches, what 'report eligibility gaps' produces, or what the mandate gate requires in practice.

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 dense sentences with the core action front-loaded, and the constraint sentence kept short. Some jargon ('strong visible semantic official-award evidence') costs a little clarity but nothing is redundant.

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?

There is no output schema and no annotations, so the description must carry everything, and it covers purpose plus key safety constraints. It still omits parameter meanings and any indication of what a match result or eligibility gap report contains, leaving an agent under-informed for a 3-parameter tool.

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

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

Schema description coverage is 0% for all three parameters (limit, query, buyer_limit). The description hints at query semantics via 'exact CPV or strong visible semantic' matching, but limit and buyer_limit are entirely unexplained, so the description does not compensate for the coverage gap.

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?

Specific verb (match) and resources (qualified live Buyer demand to suppliers), plus the matching criteria (exact CPV or semantic official-award evidence). It is distinguishable from siblings like qualify_buyer_demand and verify_supplier_public_evidence, though it never names an alternative to differentiate further.

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

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

No explicit when-to-use statement, no prerequisites, and no named alternatives among the many sibling tools. The phrase 'qualified live Buyer demand' weakly implies this runs after qualification, but the agent must infer when to pick this over qualify_buyer_demand or verify_supplier_public_evidence.

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 behavioral burden, and it does disclose genuinely useful traits: it is 'fail-closed' and 'cannot sign, send or activate a mandate,' signaling a non-committal preparation step that respects eligibility review. It omits whether any state is persisted, what permissions are required, and what happens to unmatched or incomplete input, so it is partial rather than complete.

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 compact sentences, front-loaded with the core action and followed by the safety constraint. No filler, though 'fail-closed' and 'draft view' are jargon that slightly obscure rather than clarify.

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?

No output schema, no annotations, and three opaque nested parameters mean the description should do far more work. It does not explain required inputs or the returned artifact, leaving the agent unable to invoke this correctly beyond the conceptual intent.

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 0% and three nested parameters (match, evidence, commission_terms) are entirely undocumented. The description mentions none of them, so it fails to compensate for the coverage gap. An agent has no idea what shape 'match' or 'evidence' should take.

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 verb ('prepare') and a resource ('commission mandate draft'), which is more than a restatement of the name. However, 'draft view' is ambiguous about whether this produces a read-only preview or a persisted draft, and it never distinguishes itself from the sibling submit_commission_mandate. Purpose is implied but not sharply defined.

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?

There is no explicit when-to-use guidance and no routing to alternatives such as submit_commission_mandate. The statement about 'authorized eligibility review' is a constraint, not usage guidance. The agent must infer when this preparation step is called versus its submission counterpart.

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 behavioral burden, and it does disclose one genuinely useful trait: 'It never sends contact automatically,' which reassures the agent no irreversible external action occurs. However, it omits permissions, persistence, rate limits, and what state (if any) is created, so the disclosure is partial.

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 tight sentences with the core purpose front-loaded and no filler. The non-send caveat is placed second, which is reasonable. It is appropriately sized, though it sacrifices detail for brevity.

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 four undocumented parameters, no annotations, and no output schema, the description is too thin. It names output artifacts (request, correlation id, deadline, response schema) but never explains the inputs or how the request is scoped, leaving clear gaps.

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

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

Schema description coverage is 0% and the description says nothing about the four parameters (limit, query, buyer_limit, supplier_limit). The agent must guess the meaning and filtering semantics of each, and the description does not compensate for the schema's silence.

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?

States a specific verb ('Prepare') and a concrete resource: the supplier-facing eligibility evidence request, correlation id, deadline, and response schema. The purpose is clear, but the description does not distinguish it from the near-identical sibling prepare_supplier_eligibility_request, leaving ambiguity about which one to call.

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?

There is no explicit when-to-use context, no prerequisites, and no guidance on how this differs from prepare_supplier_eligibility_request or when to follow up with the intake_* siblings. The only implied usage is that it's a preparation step preceding outreach.

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 one important behavior: the tool does not send the proposal. However, 'prepare' is vague and unqualified, with no mention of side effects, persistence, required context, permissions, or 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 a single sentence with no filler and front-loads the core action. It is concise, though it sacrifices detail that the other dimensions need.

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 5 parameters, no required fields, no annotations, no output schema, and 0% schema description coverage, a one-line description is materially insufficient for correct invocation. The agent lacks information about parameter formats, required inputs, return values, and constraints.

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 0% for all 5 parameters, and the description adds no explanation of endpoint, prospect_id, prospect_name, value_proposition, or commission_request. With additionalProperties allowing arbitrary properties, the agent receives virtually no semantic guidance for parameters.

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

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

The description states a specific verb-resource pair ('Prepare ... partner onboarding proposal') and explicitly says the proposal is not sent. This helps distinguish it from a sending/submitting tool, though it doesn't explain what 'prepare' actually produces or persists.

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?

There is no explicit guidance on when to use this tool instead of siblings like submit_partner_application. The phrase 'do not send' implies a pre-submission step, but no conditions, alternatives, or workflow context are given.

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

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

With no annotations, the description carries the full behavioral burden and does disclose important negative behavior: it does not send the request and does not mark eligibility or commission agreement verified. That is genuinely useful, but it omits permissions, idempotency, and what the prepared request contains, so coverage is only partial.

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 tight sentences, front-loaded with the action and immediately followed by the non-effect caveats. Nothing is wasted, though it is arguably too terse given the undocumented parameters.

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?

No annotations, no output schema, and three completely undocumented parameters leave significant gaps: the agent knows what the tool does not do but not what it returns or how to shape inputs. For a tool with this many unknowns, the description should do more.

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?

Three parameters (limit, query, buyer_limit) exist at 0% schema description coverage, and the description supplies no information about any of them. An agent cannot infer what 'query' filters or what the two limits control.

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?

States a specific verb+resource: 'prepare ... a supplier eligibility evidence request,' and qualifies it as a non-sending draft step. The scope ('capability-verified suppliers with public contact routes') sharpens it, but it does not name any sibling (e.g., verify_supplier_public_evidence) to differentiate itself explicitly.

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 'Prepare but do not send' and the target population ('capability-verified suppliers with public contact routes') imply when this tool applies, giving a precondition. However, there is no explicit when-to-use/when-not or routing to an alternative tool such as verify_supplier_public_evidence.

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, but it is extremely thin. The line 'MARS remains intermediary only' gestures at MARS's neutral role, but its operational meaning is vague. Nothing is said about what 'review' involves, whether the submission is editable or retractable, what side effects occur, or what conditions must hold before submitting.

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 primary action in the first sentence. However, the second sentence, 'MARS remains intermediary only,' spends its words on a cryptic phrase that adds little actionable value. Brevity here comes at the cost of necessary detail, making it under-specification rather than disciplined conciseness.

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 5-parameter tool with a nested object, no required parameters, no output schema, no annotations, and 0% schema coverage — yet the description provides only two short sentences. An agent has no way to know what data to populate, what the review flow is, what the response will contain, or how this relates to the precheck and offer tools. The definition is a bare stub relative to the tool's complexity.

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 0% and the description adds zero parameter-level information. The five parameters (subject, currency, owner_agent, requirement, jurisdiction) are entirely unexplained, including the nested 'requirement' object, which is likely the payload's core. The description 'Submit B2B demand' only weakly implies what subject/requirement might hold; the burden falls entirely on the agent to guess formats and semantics.

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 and resource ('Submit B2B demand for review'), clearly identifying the operation's subject. The word 'demand' helps distinguish it from sibling tools like publish_offer, though it never names that sibling directly. The cryptic phrase 'MARS remains intermediary only' adds some ambiguity and keeps this from a 5.

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

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

No guidance is given on when to use this tool versus the 14 siblings such as publish_offer, request_quote, or mars_deal_route_precheck. Usage is only implied (submit when you have B2B demand to review), with no conditions, exclusions, or alternative-selection criteria. For a tool in a crowded ecosystem, this is a significant gap.

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 of behavioral disclosure. It does indicate that submission enters a review workflow, but it does not state side effects, permissions, visibility, reversibility, or what happens after review. This is minimal transparency for a write/submission 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 a single sentence with no filler, and the core action and object are front-loaded. It is efficient, though quite terse relative to the tool's complexity and lack of schema descriptions.

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 five undocumented parameters, a nested object, no output schema, and no annotations, this description is far from complete. It does not explain required fields, workflow behavior, or expected response. A caller cannot confidently invoke publish_offer from this definition alone.

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 0%, and none of the five parameters (subject, currency, capability, owner_agent, jurisdiction) are explained. The phrase 'offer/capability' only gestures at the domain and adds no concrete meaning to the input schema. The presence of additionalProperties: true further increases ambiguity.

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 ('Submit'), a resource ('supplier offer/capability'), and a purpose ('for review'). This clearly conveys what the tool does and loosely differentiates it from sibling tools like publish_demand. However, it does not name alternatives or clarify what 'offer/capability' encompasses.

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?

There is no guidance about when to use this tool versus alternatives such as publish_demand, request_quote, or submit_partner_application. No conditional language, prerequisites, or exclusions are provided, leaving the agent to infer the appropriate context from the tool name alone.

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 disclose a meaningful boundary: it 'Never contacts buyers or moves money,' ruling out side effects. However it says nothing about read-only status, authentication, rate limits, or idempotency, so the disclosure is partial rather than complete.

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

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

A single dense, front-loaded sentence with no filler; the negative constraint is appended cleanly. It earns its length, though the clause pile-up is slightly hard to parse.

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?

No output schema exists, and the description usefully sketches the fields qualification yields, which partially substitutes for one. But with two undocumented parameters and no annotations, an agent lacks enough to invoke it correctly against its siblings.

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?

Both parameters (limit, query) have 0% schema description coverage, so the description must compensate — and it does not mention either param or its expected format. A caller has no idea how to scope or paginate the qualification lookup.

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?

States a specific verb ('qualify') and resource ('live Buyer demand'), then enumerates the concrete outputs (terms, deadline, supplier requirements, entry route, commission policy). It implicitly differs from discover_buyer_demand, but sibling differentiation is left to the reader rather than being explicit.

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

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

No when-to-use or when-not-to-use guidance is given. With siblings like discover_buyer_demand and mars_deal_route_precheck that could plausibly overlap, the description never says which situation selects this tool over them.

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 of behavioral disclosure. It signals that the tool records an introduction tied to a mandate, but does not disclose whether it validates the mandate's status, what side effects occur, idempotency, permissions, or failure behavior. The verb 'Record' implies a write operation, but little else is 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 a single compact sentence with no filler and the primary subject front-loaded. It is easy to read quickly, though its brevity leaves out important context that could have been included without much extra length.

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 four undocumented parameters, no output schema, and no annotations, a one-sentence description is insufficient. It leaves referral_code unexplained, does not clarify behavior when the mandate is not active or verified, and provides no indication of return values or error handling. The core purpose is stated, but the tool contract is incomplete.

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

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

Schema description coverage is 0%, so the description needed to compensate by explaining all four parameters. It loosely maps 'Buyer' to buyer_id, 'Supplier' to supplier_id, and 'mandate' to mandate_id, but it never addresses referral_code or clarifies how the parameters relate to each other. This is minimal value beyond the schema's property names.

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?

States a specific action ('Record') on a clearly defined event type ('Buyer-Supplier introduction') with an explicit condition ('under an active verified mandate'). It is not a tautology and is distinguishable from sibling tools like record_commission_event by the event described, though it does not name or differentiate a sibling explicitly.

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 only usage guidance is the phrase 'under an active verified mandate,' which implies a prerequisite but provides no direction on when to use this tool versus record_commission_event or submit_commission_mandate. There is no explicit statement about when not to use it or which alternative applies to related workflows.

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 must disclose behavior, and it does state that the tool does not move money and that it verifies before updating the ledger. However, it does not explain failure handling, idempotency, or what 'update the ledger' entails, and 'without moving money' already appears in the schema's policy. It provides useful but limited behavioral context.

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

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

The description is one compact sentence that front-loads the verification action and appends the critical no-money-movement constraint. Every phrase adds information, with no redundant or filler text.

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 involves cryptographic verification and a ledger update, yet the description omits preconditions, error behavior, and any sense of how it fits with siblings like 'submit_commission_mandate' or 'record_attribution.' There is no output schema and no annotations, so the description alone leaves significant gaps for an agent to call correctly.

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

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

Schema coverage is only 25%, with only signed_payload having a description; the description does not mention signature_algorithm, signature_base64url, or signer_public_jwk. The phrase 'principal-signed contract/payment evidence' alludes to signed_payload but does not compensate for the missing parameter documentation. The agent is left to infer cryptographic input requirements from names and schema constraints.

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 verifies 'principal-signed contract/payment evidence' and updates the 'commission evidence ledger.' This is a specific verb+resource combination, and the phrase 'without moving money' helps differentiate it from payment-related siblings. It does not explicitly name sibling tools, so it stops short of full differentiation.

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?

There is no explicit when-to-use or when-not-to-use guidance. The description only implies that the tool is appropriate when principal-signed evidence needs verification and ledger updates. It does not name alternatives or exclusions, leaving the agent to infer the context from the verb 'Verify.'

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 behavioral burden. It does disclose meaningful behavior: the RFQ is quarantined and no automatic contact will occur. However, it does not explain what quarantine means operationally, what side effects exist, or whether the RFQ can later be released.

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 tight phrase with no filler or repetition. Every word adds meaning ('quarantined', 'without automatic contact'). It is very concise, though it may be too terse for the tool's complexity.

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

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

The description is far too incomplete for a tool with 4 parameters (one a nested object), no parameter descriptions, no annotations, and no output schema. It does not explain required concepts, parameter usage, return values, or the quarantine lifecycle.

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 0% and the description provides zero information about offer_id, demand_id, requirements, or requester_agent. An agent has no help understanding what values are expected or how the parameters relate to the RFQ creation.

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 action ('Create') on a specific resource ('RFQ') and adds two meaningful qualifiers ('quarantined', 'without automatic contact') that set it apart from a generic request_quote tool. It does not fully define 'quarantined', and the qualifiers are not enough to differentiate it from every sibling without deeper inspection.

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?

There is no guidance on when to use this tool versus alternatives such as publish_demand or find_counterparty. No mention of prerequisites, typical scenarios, or situations where this tool should be avoided.

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?

There are no annotations, so the description carries the full burden. 'Verify and record' does disclose a two-step behavior: cryptographic verification and persistence. However, it does not mention what happens on verification failure, whether recording is idempotent, any authorization requirements, or the response/return behavior.

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

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

The description is a single front-loaded sentence with no filler words. It efficiently communicates the core action and object, and every word contributes to the meaning.

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

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

This is a cryptographic verification tool with four required parameters, nested objects, and no output schema or annotations. The one-line description does not address verification-failure behavior, side effects of recording, return values, or schema-encoded policy constraints, leaving important operational context 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 only 25%, so the description must compensate, but it adds little per-parameter meaning. The 'principal-signed ECDSA P-256' phrasing roughly maps to signer_public_jwk and signature_algorithm, yet those are already suggested by the schema enum and signed_payload description. It does not explain signature_base64url or the full required signed_payload structure.

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 identifies a specific action ('Verify and record') and a specific resource ('principal-signed ECDSA P-256 commission mandate'), which clearly distinguishes it from the sibling recording tools by emphasizing the signed mandate. It does not explicitly name those siblings, but the resource and cryptographic context are precise enough to avoid confusion.

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

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

The description implies the tool is used when a principal-signed ECDSA P-256 mandate needs to be verified and recorded, but it provides no explicit when-to-use or when-not-to-use guidance and does not reference any alternative tools. Usage context is inferable rather than stated.

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 does indicate that the application goes through identity and terms review, which implies a review workflow, but it does not disclose outcomes, required approvals, side effects, or what the caller should expect after submission.

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, front-loaded sentence with no filler. It conveys the core action and purpose economically, which is ideal for quick agent scanning.

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 10 parameters, 0% schema description coverage, no annotations, and no output schema, this description is severely underspecified. An agent cannot reliably know which parameters are required, what format they should take, or what happens after submission.

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 0% and the description adds no concrete meaning to any of the 10 parameters. It does not explain which fields are needed, how the const values relate to the referral-only model, or what values are expected for string parameters like contact_uri or commission_model.

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

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

The description clearly identifies the action ('Submit'), the resource ('supplier/referral partnership application'), and the purpose ('for identity and terms review'). It is specific enough to differentiate this from commission-mandate or offer-publishing siblings, though it does not explicitly name alternatives.

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

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

No guidance is provided about when to use this tool versus siblings such as submit_commission_mandate or prepare_onboarding_proposal. The description only states what the tool does, not when it should be chosen or what prerequisites apply.

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 exist, so the description carries the full burden. It usefully discloses that this is a read of public sources and that it prepares but does not send a request, and that self-published material is not eligibility proof — a real guardrail. It says nothing about permissions, rate limits, or what the prepared artifact looks like.

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

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

A single front-loaded sentence with no filler, but it is dense and compresses two distinct actions plus two negative constraints into one clause chain, making it harder to parse than necessary.

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 annotations, no output schema, and four entirely undocumented parameters, the description leaves too much unspecified for a tool that reads external sources and produces a prepared request artifact. The safety caveat is covered, but the operational surface is not.

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?

Four parameters (limit, query, buyer_limit, supplier_limit) exist at 0% schema description coverage, and the description mentions none of them or what they bound. An agent cannot tell what 'buyer_limit' vs 'supplier_limit' vs 'limit' control.

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+resource: reads public supplier websites for contact and capability evidence, then prepares a narrower formal eligibility request. This is distinguishable from siblings like prepare_supplier_eligibility_request, though the description never names the sibling directly.

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?

Usage is only implied via the constraint 'without sending it or treating self-published material as formal procurement eligibility proof', which hints at a pre-qualification step distinct from submitting a request. There is no explicit when-to-use statement or named alternative.

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