trust-tools

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

With no annotations, the description carries full behavioral burden and does so excellently: it discloses determinism, the optional model-written narrative, caching, public scope, that the narrative is never required, and that the function reads no data. This gives an agent a clear safety and side-effect profile.

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 tightly packed sentences with no filler. The core purpose is front-loaded, followed by the optional behavior and a side-effect guarantee. Every clause earns its place.

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

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

For a simple pure function with two parameters and no output schema, the description is complete: it explains what will be returned conceptually, when narrate is needed, and that no data is read. Nothing an agent needs to invoke it correctly is missing.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains that narrate:true yields a one-line model-written narrative that is cached, public-scope, and never required, and that the rating is treated as a pure function. This helps the agent understand the optional parameter's behavior without opening the schema.

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

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

States a specific verb and resource: explain what an Obelisk Rating number means, including trust band, scan score contribution, and movement drivers. This clearly distinguishes it from sibling tools that produce ratings (scan_trust, get_org_rating) rather than interpret them.

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 call context clear: use this when you have an Obelisk Rating number and need its meaning, and it clarifies that narrate is optional. It does not explicitly name sibling alternatives or exclusion conditions, but the purpose is unambiguous enough that an agent can route correctly.

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 full burden. It discloses that it reads public data (non-destructive) and specifies exact fields, which gives good transparency. However, it doesn't mention rate limits, authorization needs, or what happens if the gate is unreachable. A score of 3 is appropriate for providing clear scope but lacking deeper behavioral details.

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, no wasted words. The first sentence front-loads the verb and resource with specifics, and the second sentence clearly delineates the boundary. Every word serves a purpose.

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 has no parameters, no output schema, and no annotations, the description is quite complete for a read-only facts tool. It lists all key data points and sets clear boundaries. It slightly lacks mention of error cases or availability patterns, but for the complexity level, this is adequate.

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 0 parameters, and schema coverage is 100%, so no parameters need documentation. The description adds meaning beyond the schema by explaining the tool's purpose and what data it returns. Baseline for 0 parameters is 4, and the description provides clarity on the return content.

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 reads the Gate's public liveness facts and lists specific data points (issuer, served code revision, OIDC availability, supported protocols). The verb 'Read' and resource 'Gate's public liveness facts' are specific, and the scope is well-defined. The sibling tools like 'scan_trust' and 'verify_token' have different purposes, so this stands out.

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 for checking public liveness facts (e.g., OIDC status) without analyzing internal posture. It also states 'No posture internals,' which hints at what it doesn't do, but it doesn't explicitly name when-not-to-use or compare to siblings. The sibling set is diverse, so differentiation is somewhat inherent.

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, and it does substantial work: 'public' implies a non-mutating, accessible operation, and the 'never...never...' clause sets important expectations about what the response is and is not. It does not mention error behavior or authorization, but those are minor for a simple public read.

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 short, front-loaded sentences. The first names the action and resource, and the second compactly conveys output structure plus disclaimers with no wasted 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 single-required-parameter tool with no output schema, the description is mostly complete: it tells the agent what to pass, what it returns, and what it never returns. Minor details like not-found or malformed proof_id behavior are not covered, but the agent has enough to invoke and interpret the result.

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

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

Schema description coverage is 100%, and the existing proof_id description already explains it as an opaque id from an /agent/<proof_id> link. The description only reaffirms 'opaque proof id,' adding no extra semantic 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 states a specific action and resource: 'Read an Obelisk agent's public proof vector by opaque proof id'. It clearly differentiates from sibling trust-and-verification tools by stating it returns 'independent claims with freshness and scope; never a scalar trust score or a claim of non-humanness.'

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 reading context: use this to fetch proof claims, not to get a trust score or non-humanness verdict. It does not explicitly name sibling alternatives such as verify_agent_run_proof or get_org_rating, so the when-not guidance is implicit rather than direct.

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 full burden. It clearly discloses the return includes a score (0-100), trust band, and trend, which informs the agent about the structure of the response. It does not explicitly state that it is read-only, but the verb 'Read' implies no destructive action. The description adds value beyond the schema by detailing the output components.

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, focused sentence that conveys the exact purpose and output without redundancy. Every word is relevant and valuable.

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 has only 1 required parameter, no nested objects, no output schema, and no annotations, the description provides sufficient context for an agent to invoke it correctly. The sibling tools like 'explain_rating' may offer alternative explanations, but the description's clarity on the public nature and output format makes it complete for this simple 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 schema has 1 parameter with 100% coverage via its description, so baseline is 3. The description adds that the slug is for a 'registered organization' and provides an example ('acme'), giving context about what a slug represents and its format. This adds value beyond the schema's description alone.

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 specifies the verb 'Read', the resource 'public Obelisk Rating', and distinguishes from siblings like 'explain_rating' which likely explains the rating rather than reading it. The mention of 'public' also differentiates it from tools like 'gate_status' or 'scan_trust' which may involve private or scanning operations.

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

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

The description explicitly states that this is for reading a *public* rating for a *registered* organization by its slug. It does not mention when not to use it, but the context of 'public' implies it is for general queries, and siblings like 'explain_rating' may be alternatives for explanation. No explicit exclusions are provided, but the clarity of the public nature and requirement of a slug provides good 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly declares the tool is read-only and SSRF-guarded, which is excellent transparency for a security scanning tool. The only minor gap is not specifying output size or timeout behavior, but the terms 'Read-only' and 'SSRF-guarded' are sufficient for safe 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?

The description is extremely concise, single sentence with a dash and two additional attributes. Every element adds meaning: action (run scan), target (https URL), subject (TLS/security-header posture), result (Obelisk Rating), and safety flags (read-only, SSRF-guarded). Zero waste.

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

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

The tool is simple with one param, good schema coverage, and no output schema. The description covers purpose, scope, and safety but lacks return format details (e.g., whether rating is a string/number/range). However, given with sibling tools like explain_rating, the agent can infer the rating is a defined type. Sufficient for a straightforward scan tool.

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

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

Schema description coverage is 100%, meaning the schema already documents the one parameter (url). The description adds the constraint 'https URL' and provides a concrete example, which is useful but not extensive. Baseline 3 is appropriate since the schema already does the primary documentation work.

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 performs an Obelisk public trust scan on an https URL, assessing TLS and security-header posture and scoring it as an Obelisk Rating. This specific verb+resource combination ('run Obelisk's public trust scan') effectively distinguishes it from sibling tools which cover explaining ratings, gate status, organization ratings, etc.

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 indicates when to use the tool (on https URLs for trust scanning) but does not explicitly state when not to use it. While alternatives are implied through sibling tools like explain_rating, no direct exclusions or comparative guidance is provided.

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 must carry the full behavioral burden. It discloses the tool is read-only ('Read'), references a public endpoint ('same data as /.well-known/obelisk-transparency.json'), and explains the verification purpose. A minor gap is not mentioning if any auth or rate limits apply, but the description provides strong transparency given no annotations.

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

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

The description is two sentences with no wasted words. It front-loads the action ('Read the current signed transparency head') and immediately provides the use case and a reference to the public endpoint.

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, no-output-schema tool, the description is remarkably complete. It explains what the tool returns (signed transparency head), why to use it (verification), and where equivalent data lives. The only minor gap is not stating the return format (e.g., JSON object details) which would be helpful but not critical given the public endpoint reference.

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 the schema has 100% coverage (empty). There is nothing to document, so the description cannot add extra meaning; baseline 3 is appropriate as the tool requires no input.

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

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

The description clearly states the tool reads the current signed transparency head of Obelisk's tamper-evident receipt ledger. It specifies the verb 'read', the resource ('transparency head'), and the unique purpose (proving history only extends), which distinguishes it from siblings that deal with ratings, tokens, or scans.

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 this tool is for verification use cases ('pin it and compare later to prove history only extends'), giving clear context. However, it does not explicitly say when NOT to use it or list alternative tools, though the sibling tools are different enough that confusion is unlikely.

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 so well: it enumerates the checks performed, warns that an unsigned envelope is only consistency-checked and never verified, discloses the unsalted-v1 warning for legacy v1 envelopes, and states that raw task data is neither revealed nor inferred.

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?

Front-loaded with the core action and the token requirement, and every sentence conveys verification behavior rather than filler. It is dense but slightly overlong, with the 'anyone can build one' rationale being optional color.

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 nested-object, no-output-schema tool with zero annotations, the description covers what is verified, what is never reported as verified, and what warning metadata is emitted. It does not describe the overall response shape, but the substantive behavioral gaps are filled.

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

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

Schema coverage is 100%, so the schema already documents all four parameters in detail; the description largely restates that run_proof_token is the verifying input. It adds no semantics for expected_agent_id or expected_audience, so this sits at the baseline for full schema coverage.

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

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

States a specific verb (verify) and resource (Obelisk run proof), and immediately distinguishes the operation from the sibling verify_token/get_agent_proof by describing exactly what is checked: signature against published keys, agent liveness, key match, and delegation hops.

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 tells the agent that run_proof_token is 'the only input that can verify' and that a bare run_proof envelope is never reported as verified, which is clear when-to-use guidance. It does not, however, contrast itself against the sibling verify_token, so the agent must infer the boundary between the two.

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

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

Since no annotations are provided, the description carries the full burden. It clearly communicates that the tool verifies token origin, signing algorithm, and issuer, and explicitly states it never returns secrets (addressing security transparency). No contradictory statements exist.

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

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

The description is a single, dense sentence that conveys purpose, verification criteria, output types, and a critical security guarantee. No filler words or redundancy. The information is front-loaded and every part 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 single-parameter verification tool with 100% schema coverage and no output schema, the description is nearly complete. It covers what is verified, what is never returned, and the output constituents. Minor gap: it does not mention whether the tool returns a simple boolean, a data object, or an error message on failure.

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

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

Schema description coverage is 100%, so the baseline starts at 3. The description adds meaningful context beyond the schema: it specifies the token format ('compact-serialized JWT'), acceptable token types ('id_token or access token'), and the issuer ('issued by Obelisk'). This provides concrete usage guidance.

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 ('Verify that a JSON Web Token was minted') and clearly identifies the resource ('this Obelisk Gate') along with key verification criteria (ES256, correct issuer). It also lists the outputs (type, subject, assurance, principal), effectively distinguishing it from sibling tools like explain_rating or gate_status.

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

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

The description explicitly states what the tool does (verify token from Obelisk Gate) and what it does not do ('Never returns secrets'). It implies when to use it (whenever a token needs validation against the Obelisk Gate) but does not explicitly specify when not to use it or mention alternatives among siblings.

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