Ventru

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

With no annotations, the description carries the full behavioral burden. It discloses that the output is an Ed25519-signed capsule with route bodies, but it does not state whether the operation has side effects, requires authentication, can fail, or what the capsule's lifecycle is.

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 wasted words. It is efficient, though arguably too terse for a tool with four undocumented parameters and no output schema.

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

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

Given the absence of annotations, output schema, and schema parameter descriptions, the description is incomplete. It omits parameter meanings, usage context, error behavior, and the structure of the returned capsule beyond a high-level phrase.

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 explain the four parameters. It only clearly relates to 'intent' and vaguely to 'requireVerified' via 'verified providers'; it does not explain 'agent' or 'location'.

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 and resource: ranks verified providers for an intent and returns an Ed25519-signed capsule with ready-to-call route bodies. This is clear enough to distinguish it from general search or create-route siblings, though it does not explicitly name an alternative.

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 siblings such as ventru_search_providers or ventru_create_route. The phrase 'for an intent' implies context but does not provide explicit usage conditions, prerequisites, or 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?

With no annotations, the description carries the full burden and does substantial work: it discloses the side effect that a pending invite is created for non-Ventru recipients, that a thread is started, that replies are free, and that from+token produce a verified sender. It omits failure modes (what happens with an invalid token or unknown domain) and any rate limits, keeping it at 4.

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?

Four tight sentences with the core action front-loaded, followed by thread/cost behavior, sender verification, and the invite fallback. No sentence is redundant and nothing is buried.

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 7-parameter mutation tool with no annotations and no output schema, the description covers the important unknowns: the invite side effect, thread continuation, and verified-sender mechanics. It does not describe what the call returns (thread ID, delivery status) or error conditions, which leaves a modest gap.

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

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

Schema coverage is 71%, and the description adds real meaning beyond it: it clarifies the accepted formats for 'to', explains where 'from' and 'token' come from (ventru_register), and states that threadId continues an existing thread. The 'intent' and 'router' parameters are left to their schema descriptions, which already cover them adequately.

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 and resource ('Send a signed message to any Ventru address') and enumerates the accepted address forms (@name, agent:..., verified business domain). That plus the thread semantics distinguishes it cleanly from ventru_inbox (reading) and ventru_find (discovery).

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?

Gives clear operational context: pass your own address and token from ventru_register for verified sending, and use threadId to continue a thread rather than start a new one. It stops short of an explicit 'use X instead when…' exclusion against siblings like ventru_create_route, so it lands at 4 rather than 5.

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

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

With no annotations, the description carries the full burden. It usefully discloses that a routeId is returned and that outcomes should be reported via ventru_report_outcome, but it omits whether recording a route creates any commitment, whether it is idempotent, and what permissions the user_approved mode requires.

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 action and the return value front-loaded. No filler, every clause carries information.

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

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

For a 6-parameter creation tool with no annotations and no output schema, the description is far too thin: parameter meaning, preconditions, and side effects are all missing. An agent cannot reliably invoke this correctly from the description 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% across 6 parameters, so the description must compensate. Only the authorization parameter is loosely echoed via the "quote-only or user-approved" phrasing; providerId, offerId, intent, capsuleId, and agent are left entirely unexplained.

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

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

Names a specific verb and resource ("Record a ... route to a provider offer") and clarifies the two authorization modes. It does not explicitly distinguish itself from sibling tools beyond the mention of ventru_report_outcome, so it falls short of the top mark.

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?

Implies usage through "quote-only or user-approved" and redirects follow-up reporting to ventru_report_outcome. However it never states when an agent should create a route versus using ventru_find, ventru_search_providers, or ventru_build_action_capsule first, and no exclusions or prerequisites 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 readOnlyHint=true already declaring safety, the description adds real behavioral context: the scope covers thousands of external MCP servers and the returned values are contactable addresses or server URLs. It does not mention result limits, ranking, or pagination, but for a search tool the disclosure is above baseline.

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, and the trigger condition is front-loaded before the enumeration of result types. Dense but nearly every clause carries information; the parenthetical about MCP servers is the only slightly verbose portion.

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 carries the return-value burden, and it does so by naming both return kinds (Ventru addresses, MCP server URLs) and the tool that consumes them. What remains missing is result ordering, quantity limits, and how 'type' interacts with the other result kinds.

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 67% and the schema itself documents all three parameters including the type enum and an example-filled query. The description adds light framing (that results include a person's public address, and that queries can target capabilities) but no syntax or guidance specific to 'area' or 'type'. A baseline 3 is appropriate.

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

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

The definition uses a specific verb ('Find') plus the resources it searches: AI agents by capability, verified businesses, people with a public Ventru address, and public MCP servers. It falls short of a 5 only because it never names the nearest sibling (ventru_search_providers or ventru_resolve_agent), which an agent could plausibly confuse with this tool.

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

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

The opening clause ('Use when the user needs someone or something to talk to, hire, delegate to, or buy from') gives a concrete triggering situation, and the last sentence routes the agent to ventru_contact for the follow-up action. It stops short of exclusions — nothing says when to prefer ventru_search_providers or ventru_resolve_agent instead.

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?

readOnlyHint=true already tells the agent this is a safe, non-mutating read. The description adds only the message scope (including thread replies); it says nothing about pagination, result volume, ordering, whether messages are marked read, or what the required token represents as an auth requirement.

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?

One tight sentence with the resource and scope front-loaded and no filler. It is efficient, though the brevity is partly under-specification rather than discipline.

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, 0% schema coverage on two required params, and only a readOnlyHint annotation, the description should carry more weight. An agent still cannot determine what 'token' is, how results are shaped, or whether the inbox is paginated.

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 both required parameters are undocumented. The description only obliquely explains 'address' via 'your Ventru address' and gives no meaning at all for 'token' (presumably an auth credential), which is the highest-risk gap for correct invocation.

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?

Uses a specific verb ('Read') plus resource ('messages sent to your Ventru address') and scopes it with 'including replies to threads you started'. It is clearly distinguishable from siblings like ventru_contact or ventru_find, though it never explicitly names a sibling to route away from.

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 to call this versus alternatives (e.g., ventru_contact for sending, ventru_find for discovery), and no prerequisites beyond the implicit need for an address. Usage is only inferable from the tool name and 'inbox' framing.

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 is consistent with readOnlyHint=true and adds a substantive domain rule the annotations cannot express: 'People never pay' is a pricing-policy fact, not a mutability fact. It does not describe response shape, but for a static reference lookup with a read-only annotation, that omission is minor.

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, the core subject (who pays, by connection direction) is front-loaded, and the qualifier follows. 'People never pay' is terse to the point of being slightly cryptic out of context, 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?

For a zero-parameter informational tool with no output schema, the description covers the substance of what an agent gets back: which direction of connection incurs payment, what each plan contains, and the global rule that individuals never pay. Nothing further is required to decide whether to call it.

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 takes no parameters, so there is nothing for the description to disambiguate. Baseline of 4 applies since the schema cannot be a source of misuse here.

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 resource (pricing/plans) and a specific scope (connection direction, plan contents) with the verb 'explain'. It is distinguishable from siblings like ventru_usage and ventru_trust_profile, though it never names them 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?

Usage is implied rather than stated: an agent can infer this is the reference lookup for pricing questions. There are no explicit triggers, no exclusions, and no pointer to ventru_usage for actual consumption/billing volume, which is the nearest sibling and a plausible source of confusion.

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 openWorldHint=true, so the agent knows this is a safe outbound read. The description adds that results report 'what is missing,' but says nothing about failure behavior for unreachable sites, timeouts, or how many requests are made—useful context for an open-world fetch.

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 sentence that front-loads the action and enumerates the checked artifacts with zero filler. Every clause carries information.

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

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

There is no output schema, so the description bears responsibility for describing the return value; it only gestures at it ('what is missing') without stating the shape of the result (per-artifact found/missing status). Adequate to call, but not complete for interpreting 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?

Only one required parameter and schema description coverage is 0%, but 'business website' makes the intent of url fairly evident. It does not specify format expectations (scheme, trailing path), so it adds little beyond the schema; baseline 3 for an obvious single 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?

States a specific verb ('Check whether') and a specific resource (a business website), plus enumerates the exact artifacts being probed (llms.txt, agent.json, OpenAPI, A2A agent card). None of the sibling tools overlap with this capability, so an agent can select it unambiguously.

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 by the purpose sentence; there is no explicit 'use this before calling X' or 'use when you need to qualify a provider' guidance. It also omits prerequisites such as whether the URL must include a scheme or be a root domain.

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 whole burden: it does disclose that the address is free, that the call is one-shot, and that the response contains inboxToken and recoverySecret — meaningful, non-obvious behavior. It says nothing about username collisions, whether the claim is permanent/reversible, rate limits, or what failure 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?

Two tight sentences, front-loaded with the purpose, followed by the operational instruction. No filler or redundancy.

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

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

Useful that it names the returned credentials in the absence of an output schema, and the one-shot nature is stated. But with six parameters, no annotations, and low schema coverage, an agent is left without guidance on parameter choice or register failure modes.

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 33% — only listed and description are documented in the schema. The description adds no meaning for username, name, ownerType (agent vs human), or capabilities, all of which an agent must guess at. It fails to compensate for the coverage gap on a 6-parameter 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?

States a concrete verb+resource: claim a free @address and inbox. The beneficiary ("you or your user") and the reachability goal make the intent unambiguous. It doesn't explicitly contrast with siblings such as ventru_inbox or ventru_resolve_agent, so it stops short of full sibling 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?

"Call once" is explicit invocation guidance, and the instruction to store credentials securely tells the agent how to behave after the call. There are no exclusions or named alternatives for when a different tool (e.g., ventru_create_route) is more appropriate, so it falls short of the 5 bar.

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 does disclose a key behavioral trait: outcomes tied to a recorded routeId affect AgentRank and attribution. Yet it omits permissions, idempotency, consequences of repeated reporting, and what the response looks like, 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 sentences, front-loaded with the tool's purpose, and no redundant or filler content. The second sentence adds critical context about routeId significance without wasting words.

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

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

For a mutation tool with 6 parameters, no annotations, and no output schema, the description leaves too many gaps: parameter semantics, permissions, idempotency, and expected response are all absent. The AgentRank note is helpful but insufficient for this 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% across 6 parameters. The description implies the status values and stresses the importance of routeId, but it leaves providerId, value, summary, and currency completely unexplained and does not compensate for the lack of schema 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 a specific verb ('Report') and resource ('routed request outcome') and enumerates the three statuses (completed, failed, disputed). It clearly conveys the tool's function, though it does not explicitly differentiate from sibling tools such as ventru_create_route or ventru_build_action_capsule.

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 after a route has been recorded ('Only outcomes tied to a recorded routeId') and explains the condition under which the report matters. However, it does not state when not to use this tool versus alternatives, nor does it name any sibling tool for comparison or exclusion.

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?

readOnlyHint=true already tells the agent this is a safe read. The description contributes real value by enumerating the response facets (registration, inbox, transport status), but it omits what happens on an unknown address (error vs. empty result) and any auth or rate-limit constraints on the lookup.

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 the action, the input example, and the output contents. No filler or repetition.

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

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

For a one-parameter read tool with no output schema, the description covers the essential concerns: what to pass in and what categories of data come back. The only meaningful gap is not-found/error behavior, which is minor given the tool's simplicity and the readOnly annotation.

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

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

The schema has 0% description coverage, so the description must carry the single parameter. It does partially: "@name" gives the expected address form, which the bare string type does not. However, format rules for the address (domain-like vs. handle, casing, validation) remain unspecified.

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 gives a concrete verb ("look up") and resource ("an agent address such as @name") and even states the returned data (registration, inbox, transport status). It is specific enough to act on, but it does not distinguish itself from plausible siblings such as ventru_find or ventru_search_providers, so an agent must infer which lookup tool is appropriate.

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: the reader infers this is the tool for resolving a known @address rather than searching. There is no explicit when-to-use, no when-not-to-use, and no named alternative among the many siblings (find, search_providers, trust_profile).

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 useful behavioral context beyond the annotations: verified-only default, trust evidence and freshness in results, empty-result meaning, and the side effect that unmet demand is recorded. This is consistent with readOnlyHint=false because recording unmet demand is a write 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 three sentences, front-loaded with purpose and followed by return and empty-result semantics. Every sentence adds useful information without redundancy.

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

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

With no output schema, the description carries most of the return-value burden and does explain verified-only results, trust evidence, freshness, and empty results. It is slightly incomplete on pagination or result limits, but overall sufficient for an agent to invoke the tool correctly.

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

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

Schema description coverage is 75%, so most parameters are already documented. The description does not add meaning for area, agent, category, or how query maps to matching, so it does not compensate for the remaining 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?

The description states a specific verb and resource: find businesses on Ventru matching a request. It also clarifies that results are verified providers by default, which distinguishes it from a generic search or trust lookup.

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

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

The description implies when to use the tool by saying it finds businesses matching a request. However, it does not explicitly contrast this with sibling tools such as ventru_find or ventru_trust_profile, nor does it 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?

The readOnlyHint annotation already establishes that this is a safe read operation. The description adds useful behavioral context by noting that it returns evidence and review currency, but it does not describe output structure, freshness semantics, or limitations.

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 three tightly scoped clauses and no wasted text. Every clause describes a distinct part of the returned information.

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

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

For a zero-parameter, read-only informational tool with no output schema, the description adequately explains what will be returned: label meanings, evidence, and currency. It could be slightly more complete by indicating the shape or granularity of the returned trust profile.

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 takes zero parameters, so parameter semantics are not applicable. The baseline score of 4 is appropriate because there is no parameter ambiguity to resolve.

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 and resource: it returns the meanings of Ventru assurance labels, the evidence behind claims, and whether the review is current. This clearly differentiates the tool from the action-oriented 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?

There is no explicit when-to-use guidance, no exclusions, and no named alternatives. The content implies it is for understanding trust labels, but an agent must infer the usage 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?

readOnlyHint=true already covers the safety profile. The description adds real context beyond that: results are aggregated (not raw request rows) and ranked by frequency of absence of a verified provider. It omits anything about the time window, aggregation granularity, or how counts are computed.

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?

One compact sentence with no waste and the ranking criterion front-loaded. It is slightly elliptical ('Aggregated requests agents made') but nothing could be cut without losing information.

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

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

For a one-optional-param read-only tool with no output schema, the description conveys the core concept. However, with no output schema and no schema param docs, the unexplained `days` window and unspecified aggregation granularity leave genuine ambiguity about what the returned numbers mean.

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 `days` has 0% schema description coverage, so the description is the only place meaning could be supplied — and it says nothing about it, neither its default horizon nor whether it filters the request timestamps or the ranking period. This is a clear compensation 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?

The sentence names a specific resource (aggregated agent requests) and its ranking dimension (how often no verified provider existed), which is meaningful and distinct from siblings like ventru_usage or ventru_search_providers. It is a noun phrase rather than an explicit verb+resource, but the reporting/read intent and scope are recoverable without opening the schema.

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 usage guidance is given: nothing says when to pick this over ventru_usage or ventru_find, or what question this answers. The agent must infer that this is for spotting supply gaps rather than for individual provider lookups.

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?

readOnlyHint=true already declares this is a safe read, and the description is consistent with that ('Show'). It adds useful detail about what data is returned (connections, allowance, fees, router credits) but says nothing about authentication requirements for the token parameter, freshness of 'this month', or whether the result covers a billing period partial-to-date.

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 that names the verb, the time scope, and the returned fields with no filler. It is efficient, though it could have spent one more clause on the token requirement.

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

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

For a two-parameter read-only tool with no output schema, the description covers the data domain adequately, but with 0% schema coverage it leaves a required authentication parameter undocumented. An agent knows what it will get back but not fully what it must supply.

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 two required parameters. The description only implies that 'address' selects whose usage is reported; the required 'token' parameter is completely unexplained, and there is no hint about its format or where it comes from.

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 and resource: it shows this month's connections, allowance, fees, and router credits for an address, which distinguishes it from siblings like ventru_pricing or ventru_find. The framing is slightly indirect ('connections' rather than 'usage/billing summary'), but the enumerated fields make the purpose unambiguous.

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

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

There is no indication of when to use this versus ventru_pricing, ventru_trust_profile, or ventru_inbox, and no prerequisites are given. The agent must infer usage from the field list alone.

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