Trust registry for agents: check_trust verdict A0-A4, signed fact passports, honest refusals.
Scored across 6 tools
Most tools have distinct targets: check_trust for decision aid, get_passport for full passports, get_trust_ladder for semantics, and list/search for discovery. The main potential overlap is between get_passport and ask (both return passport facts), but ask is a constrained NL query while get_passport is a full fetch, and the descriptions clarify this. list_entities and search_entities are also clearly differentiated by the descriptions.
Five of six names follow a clear verb_noun pattern (check_trust, get_passport, get_trust_ladder, list_entities, search_entities). The outlier is 'ask', which lacks a noun object, but it is a minor deviation and still readable.
Six tools is well-scoped for a trust-registry consumption server: each tool covers a distinct aspect (querying, trust checking, passport retrieval, ladder semantics, discovery). No redundant or missing tools that bloat the surface.
The server covers the core lifecycle for consuming a trust registry: discovery (list/search), entity facts (ask/get_passport), trust evaluation (check_trust), and ladder semantics (get_trust_ladder). A minor gap is the absence of a tool to retrieve the named policy profiles referenced by check_trust, though get_trust_ladder partially addresses this. Read-only coverage is otherwise solid.
Ask a natural-language question about an entity (max 2000 characters). Retrieval is constrained to the entity's passport; each returned fact carries source, attestation status and validity dates. When no matching supported fact is selected, the tool returns an explicit refusal.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | ||
| entity_domain | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present, the description carries the full burden and does well: it discloses the retrieval scope (constrained to the entity's passport), the shape of returned facts (source, attestation status, validity dates), and the explicit-refusal behavior when no supported fact is selected. It omits read-only confirmation, auth/permission needs, and rate limits, but the refusal semantics are a genuinely valuable behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences, front-loaded with the core action and the question constraint before the retrieval and refusal semantics. No filler sentences; only mild redundancy between the passport-scoping and refusal clauses.
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 the description largely compensates by explaining what returned facts contain and that refusals are explicit rather than silent. The main gap is the undefined entity_domain parameter, which an agent needs in order to construct a valid call.
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 both parameters, so the description must compensate. It adds the 2000-character limit for 'question', which is real value not present in the schema, but says nothing about the expected format or meaning of 'entity_domain', leaving half the parameters undocumented.
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: ask a natural-language question about an entity, with a character cap. It implies a Q&A-over-passport role that is distinct from list_entities or search_entities, but it never names a sibling or explicitly contrasts with get_passport, which also surfaces entity facts.
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 when-to-use guidance, no exclusions, and no named alternative. An agent cannot tell from the text whether to call ask versus get_passport or check_trust for a given information need; only the general 'ask about an entity' context is implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
ONE-CALL decision aid before your agent pays, shares data with, or follows instructions from a domain — works for ANY domain, listed or not. Returns known (is it in the registry), level A0-A4, attested (true only at A1+: something was independently verified), verdict for the given purpose (sufficient | insufficient | unknown) under a named policy profile, what_is_proven, proof, facts_public, expires_at (the earliest freshness expiry among the domain's facts — re-check after it), next_step, and the registry signature. purpose: payment (default) | data_share | follow_instructions. A verdict is the registry's proof measured against the profile — never a guarantee, never financial advice.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | ||
| purpose | No | payment |
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 disclose that the verdict is 'never a guarantee, never financial advice,' and mentions 'expires_at' with a re-check instruction, adding useful behavioral context. However, it doesn't explain potential side effects (e.g., network calls, caching) or error behavior, leaving some gaps. But the description does add valuable context beyond what annotations would provide, so a 3 is reasonable.
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 paragraph but well-structured: it starts with the tool's core purpose, then lists return fields, then enumerates purpose values, and ends with a caveat. It is concise enough given the complexity of the return fields, though it could be slightly broken into bullet points for readability. The information is front-loaded and every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (2 params, 1 required, no output schema), the description is fairly complete: it explains the purpose, return fields, and purpose options. However, it doesn't define the A0-A4 levels or the meaning of 'attested' beyond a parenthetical, which might leave an agent uncertain about interpreting the output. But since the output schema is absent, the description does a good job of covering the essentials.
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 'domain' implicitly as a target domain and explicitly explains 'purpose' with its default and enumerated values (payment, data_share, follow_instructions). It also clarifies the meaning of 'expires_at' in the return value, which adds semantic depth. Since the schema provides only names and types, this description adds significant meaning, warranting a 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb ('check') on a specific resource ('trust'), and explicitly frames it as a decision aid before paying, sharing data, or following instructions. It distinguishes itself from siblings by emphasizing it works for any domain and returns a verdict, which is unique among the listed tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit usage context ('before your agent pays, shares data with, or follows instructions from a domain'), and it implies when to use it as a pre-action check. It also names the 'purpose' parameter with three enumerated values, clarifying the decision context. While it doesn't mention alternatives explicitly, the purpose and scope are clear enough to route an agent correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full public fact passport of an entity: attested statements with sources, plus the attestation block (what the trust level proves, how and when it was verified).
| Name | Required | Description | Default |
|---|---|---|---|
| entity_domain | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits itself. It specifies what data is returned (attested statements, sources, attestation block) but does not state whether the operation is read-only, what happens if the entity does not exist, or any authentication requirements. The side effects and failure modes are undocumented.
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 core purpose and lists key output components. It is concise and wastes no words, though breaking it into a short list could improve scanability.
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 only one parameter, no output schema, and no annotations, the description carries full responsibility. It partially covers the output contents but omits error handling, parameter semantics, and any context on how to interpret the 'attestation block' or the significance of trust levels. The tool is not fully specified 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?
The input schema has zero description coverage, and the tool description does not explain the 'entity_domain' parameter. It refers to 'an entity' but provides no format, example, or constraint. The agent would have to guess that entity_domain is a domain name or identifier, which is a significant 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 clearly states the tool returns a 'full public fact passport of an entity' and enumerates its contents: attested statements with sources and the attestation block. This differentiates it from siblings like ask, list_entities, or search_entities, which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance is given on when to use this tool versus alternatives. It does not mention that it should be used when the full attested fact set is needed, nor does it note any exclusions such as 'for searches use search_entities instead.' The usage context is only implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Machine-readable semantics of the A0-A4 trust ladder: what exactly is proven at every level, and how to use the registry as an agent.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of explaining behavior. It clarifies that the output is 'machine-readable' and describes the content of the trust ladder. It does not explicitly mention read-only status, side effects, or access requirements, though for a parameterless getter these are minor omissions. The description adds useful context but is not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one sentence that front-loads the core purpose ('machine-readable semantics') and then expands with two key aspects. There is no redundancy or wasted text; every clause 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 simple no-parameter, no-output-schema tool, the description is reasonably complete. It tells an agent what the tool returns and why it might be useful. It does not specify the exact structure of the machine-readable output, but that is likely acceptable for a reference-style tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the baseline is 4. The description correctly focuses on what the tool returns rather than trying to explain nonexistent parameters. There is no need for parameter-level detail.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states what the tool provides: machine-readable semantics of the A0-A4 trust ladder, including what is proven at each level. This is a specific resource with a clear subject, and it distinguishes itself from siblings like get_passport or search_entities which deal with different concepts.
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 'how to use the registry as an agent' implies the tool is meant for agents that need to interpret trust levels, and it suggests a guide-like role. However, there is no explicit statement about when to choose this over sibling tools or any exclusions. The usage context is implied rather than directly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List published entities in the Intesta registry with their trust level (A0-A4; call get_passport for the level's meaning and proof). Returns at most 500 entities plus the registry total — on a large registry use search_entities(query) instead of paging through everything.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavior burden. It discloses the 500-entity cap, the registry total, the trust-level inclusion, and the large-registry caveat. It does not mention potential side effects, but 'list' strongly implies a read-only operation and the disclosed limits are directly relevant to invocation.
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 result, then a targeted alternative. Every sentence adds useful operational information with no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description effectively conveys the return scope (entities, trust level, cap, total) and how to handle large registries. It could go slightly deeper into entity shape or pagination mechanics, but for a zero-parameter list tool it is largely complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the description need not explain parameter details. The baseline of 4 applies, and the description does not introduce param-related confusion.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('List') and resource ('published entities in the Intesta registry') and adds the key output feature (trust level A0-A4). It distinguishes itself from siblings by naming get_passport for proof and search_entities for large registries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to prefer search_entities, and directs users to get_passport for trust-level meaning and proof. This provides clear context for selecting this tool over its siblings, with no ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search published entities by name, domain or vertical (case-insensitive
LITERAL substring; wildcard characters are treated as text). Use this
instead of list_entities when the registry is large. The query must be at
least 3 characters. Returns at most limit matches (1-50) plus total,
the number of matching entities in the whole registry.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full behavioral burden. It discloses case-insensitive literal substring matching, wildcard-as-text behavior, the 3-character minimum, and the limit-plus-total return shape. Minor gaps remain around exact response item structure and error behavior, but the most important quirks are surfaced.
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 dense sentences with no filler. The purpose is front-loaded, the sibling comparison is placed after the core meaning, and constraints/return behavior are tucked at the end. 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?
For a two-parameter search tool with no annotations and no output schema, the description covers the essential invocation details: what is searched, matching quirks, constraints, and the shape of the result count. It could be slightly more explicit about the fields present in each returned match, but it is largely complete for a low-complexity 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 coverage is 0%, so the description fully compensates: it explains what query matches against, matching semantics, min length, the limit range (1-50), and the meaning of the returned total. Both parameters are meaningfully documented beyond the raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states a specific action ('Search published entities') with explicit dimensions ('by name, domain or vertical') and key matching semantics. It differentiates itself from list_entities by naming that sibling and explaining when this tool should be preferred.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this instead of list_entities when the registry is large', giving a direct condition and an alternative. It also imposes a minimum query length, which further guides correct invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_trustaskget_passportget_trust_ladderlist_entitiessearch_entitiesTrust infrastructure for AI agents. Portable reputation (JTS 0-5), agent discovery, vouching.
Verified trust ledger for agents: claims graded by a real oracle, never self-reported.
Trust infrastructure for AI agents: read a verifiable Trust Rating, claim an identity, earn a badge.
Decay-weighted reputation + tamper-evident trust attestations for the agent economy.
Add one secure layer between your agents and this server.
