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

No annotations exist, so the description must carry the burden. It mentions authentication requirement (access_token or public_key_hex) and provides an example response, but does not disclose other behavioral traits like side effects (none expected), rate limits, or error behavior for failed auth.

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

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

The description is concise with a clear summary, authentication note, and example. However, the example response block is large and could be trimmed or referenced externally.

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, the example response covers key fields (agent_id, scores, scopes, pending_confirmations, active_attestations). Missing details on error responses or pagination, but these are not critical for a status snapshot.

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 parameters are only named. The description partially compensates by showing an example call with access_token and mentioning both auth methods, but does not explain when to use each or their format beyond the example.

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 comprehensive status snapshot combining identity, trust scores, pending confirmations, and active attestations. This differentiates it from sibling tools like list_pending_confirmations or list_my_attestations.

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 it's useful as a dashboard or health check but does not explicitly state when to use it versus more specific sibling tools like check_trust or get_score_breakdown. No when-not or alternative recommendations 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, description fully discloses behavioral traits: optional authentication changes output, low confidence interpretation, meaning of score 0.5 with low confidence, and score_type options. Example response clarifies return fields and computed_at timestamp.

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?

Well-structured: starts with purpose, lists return fields, details score_type options, explains authentication levels, provides example call and response. No redundant sentences; every part 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 no output schema and 3 parameters, description is fully complete. It explains all return fields, authentication differences, score_type semantics, and even provides a full example response. Covers all necessary information 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?

Despite 0% schema description coverage, the description explains all three parameters thoroughly: agent_id (required), score_type with options and defaults, and access_token with authentication behavior. Example call demonstrates parameter usage clearly.

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 checks an agent's trust score before a transaction, with specific verb and resource. It distinguishes from siblings like check_trust_batch (batch) and get_score_breakdown (detailed breakdown) by focusing on single-agent score retrieval with plain-language explanation.

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 when to use ('before entering a transaction') and describes authentication impact on returned data. Does not explicitly say when not to use (e.g., for batch operations), but the sibling list implies this. Overall, provides clear 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?

The description discloses key behaviors: batch limit, result structure (score, confidence, interaction_count), inline errors for missing agents, score_type options, and shows example input/output. However, it omits the role of the access_token parameter, which could affect authorization 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 concise and well-structured: purpose first, then constraints, result format, options, and examples. Every sentence adds value 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?

The description covers the tool's purpose, batch limit, error handling, and provides illustrative examples. The missing explanation for access_token is a minor gap, and there is no output schema, but the example response compensates well.

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 description explains agent_ids (list of UUIDs) and score_type (with enumerated options), but does not explain the access_token parameter at all. Since the schema has 0% description coverage, the description partially compensates but misses one 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?

The description clearly states the tool checks trust scores for multiple agents in a single call, with explicit mention of batch size (up to 20) and use case (reducing round-trips). This distinguishes it from single-agent 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?

The description explains when to use the tool (assessing several potential counterparties before choosing one) and implies a batch use case. However, it doesn't explicitly compare with sibling tools like check_trust or 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?

With no annotations, the description responsibly mentions return structure (scores, confidence, interaction counts) and limitation (max 10), but does not disclose authorization needs (access_token optional but unexplained) or error handling.

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?

Five concise sentences, front-loaded with purpose, no redundancy, each sentence adds information.

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

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

Despite no output schema, description covers return values and constraints. Could mention error handling for invalid IDs, but overall sufficient for agent decision-making.

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 description compensates by explaining score_type options and implying agent_ids purpose. It adds value over the schema, though access_token remains 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 clearly states the action (compare) and resource (trust scores of multiple agents), and specifically mentions returning a ranked list, distinguishing it from siblings like check_trust which is for single agent checks.

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?

Provides explicit context (useful when choosing between agents), a limit (max 10), and defines score_type options. However, it does not explicitly state when not to use or suggest alternatives like check_trust_batch for non-comparison queries.

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 provided, but description fully discloses behavior: creates matching report, sets mutually_confirmed flags, handles different outcomes, requires access_token with trust.report scope, and includes example response.

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?

Well-structured with clear sections: purpose, usage, behavior, auth, example call, example response. Not overly verbose, but could be slightly more concise.

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, example response helps. Covers auth, behavior, and outcome. However, missing explanation of context parameter and error scenarios. Still quite complete for a 4-param tool with no annotations.

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 description must compensate. Example shows interaction_id, outcome, access_token, but does not explain context parameter or possible outcome values. Adequate but missing details.

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

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

Clearly states the tool confirms a counterparty's interaction report by filing your side. Distinguishes from siblings like report_interaction and list_pending_confirmations.

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 when to use: when another agent reports an interaction involving you. Also explains you can agree or report a different outcome, but does not explicitly state when not to use.

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?

While no annotations are provided, the description thoroughly explains what the tool returns, including an example response. It implicitly indicates a read-only operation, though it could be more explicit about having no side effects.

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 well-structured with bullet points and an example, front-loading the purpose. It is slightly lengthy but each sentence adds value, making it appropriate for the 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?

Given no parameters and no output schema, the description provides a complete overview of the return structure, covering tools, auth methods, rate limits, etc. No gaps remain.

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 parameters and 100% schema coverage, there is no need for parameter explanations. The baseline for 0 parameters is 4, and the description adds no misleading information.

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 discovers AgentTrust capabilities, tools, auth methods, and rate limits. It uses a specific verb-resource pair and distinguishes itself from sibling tools by being the initial discovery endpoint.

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 'Call this first when connecting to AgentTrust' and notes 'No authentication required.' This provides clear when-to-use guidance and prerequisites.

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?

Discloses authentication requirements, scope, and consequences of frivolous disputes (trust score penalty). With no annotations, this carries full burden and handles it well.

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?

Concise yet comprehensive: purpose, instructions, warnings, return info, and example call. Every sentence adds value; 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 4 parameters, 3 required, no output schema, the description covers all necessary aspects: inputs, side effects, return structure, and example response. Missing nothing critical.

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 description must add meaning. It explains interaction_id comes from a previous report, reason must justify the dispute. The optional 'evidence' parameter is mentioned but not detailed, slightly reducing score.

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?

Clearly states 'File a dispute against an interaction outcome', identifying verb and resource. Distinguishes from sibling tools like report_interaction and resolve_dispute.

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?

Explains when to use (after a reported interaction) and provides required parameters (interaction_id, reason, access_token). Does not explicitly exclude alternatives, but context is clear.

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

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

With no annotations, the description carries the full transparency burden. It discloses that the token is signed client-side, no server-side key storage, token expiration, and the TTL clamping behavior. It does not mention rate limits or error conditions, but the provided information is sufficient for a straightforward token generation tool.

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

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

The description is well-structured with sections, bullet points, and examples. While slightly verbose, every sentence contributes meaning. The clear formatting aids readability and usability.

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 (3 parameters, no output schema), the description is remarkably complete. It covers the typical workflow, parameter details, expected response structure (including an example), and the authentication flow. No gaps are apparent.

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 fully. It does so by explaining each parameter's purpose, source (e.g., from register_agent response), format (64 hex chars for private_key_hex), and constraints (default/max for ttl_minutes). This adds substantial value beyond the bare JSON 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?

The description clearly states the tool generates a signed access token for standalone agents. It differentiates by explaining the use case (authentication) and listing which sibling tools require the token, making it distinct from similar tools like register_agent.

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

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

The description provides explicit usage context: after register_agent and before calling authenticated tools. It includes a typical agent flow and advises to repeat when token expires. However, it does not explicitly state when not to use this tool or compare with alternatives, though the specific authentication role is implied.

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 disclosure of optional authentication yielding summary vs. full detail is valuable. It covers return fields and error case, though does not mention read-only nature 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?

The description is front-loaded with purpose, then details authentication, return fields, and error response in a well-organized, efficient block with no superfluous 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?

Given no output schema, the description lists all return fields and a plausible error case, fully covering what an agent needs for a data retrieval 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?

With 0% schema coverage, the description adds meaning: agent_id is a UUID, access_token is optional and changes the response detail. This compensates well, though no format constraints are given.

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 'Retrieve an agent's public profile' with a specific verb and resource, and distinguishes from sibling tools by noting the use case for evaluating a counterparty before transacting.

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

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

It provides a clear use case ('evaluate a potential counterparty before transacting'), but does not explicitly state when not to use or name alternative tools for other needs like trust breakdown.

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 fully discloses authentication requirements, the unsanitized nature of the context field, and the presence of context_warnings for prompt injection. These are critical behavioral traits that go beyond the basic retrieval function and help the agent handle results safely.

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 organized into logical paragraphs: purpose, filtering, use case, authentication, parameter details, and security note. Each section adds value. While it's longer than ideal, it avoids redundancy and front-loads the core functionality. Minor room for tightening, but overall well-structured.

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

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

The description covers the tool's purpose, filtering options, return format, authentication, and a critical security behavior. However, it lacks explicit pagination behavior beyond the limit parameter, and does not specify possible values for interaction_type or outcome. Given no output schema, it provides enough for basic usage but not exhaustive.

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 provides defaults and limits for 'since_days' and 'limit', which is helpful. However, it omits details for 'agent_id', 'interaction_type', 'outcome', and 'access_token' (beyond stating the need for authentication). The added information is good but incomplete, leaving agents to infer or guess for several 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 clearly states the tool retrieves interaction history for an agent, explicitly noting filtering by type and outcome, and the return format (chronological list with timestamps, counterparty IDs, outcomes). This distinguishes it from sibling tools like agent_status or check_trust, 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?

The description provides clear usage context ('useful for due diligence before high-value transactions') and explicitly requires authentication via access_token. While it doesn't list alternative tools or when not to use, the given context and prerequisites are sufficient for an agent to decide. No misleading guidance.

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

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

With no annotations provided, the description fully discloses that this is a read operation, requires trust.read scope, and lists all returned fields with explanations. No contradictions.

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

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

The description is concise, uses bullet points for return fields, and front-loads the purpose. Every sentence adds value 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?

Given no output schema, the description thoroughly covers return values. For a tool with two simple parameters and clear authentication requirement, it is sufficiently complete for an agent to use 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%, meaning parameters have no descriptions in the schema. The description does not add any information about 'agent_id' or 'access_token' beyond their names. Given the lack of schema details, the description should compensate but fails to do so.

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 it returns a detailed breakdown of trust score computation, listing specific fields like bayesian_raw, dispute_penalty, etc. This distinguishes it from siblings like 'check_trust' which likely only return the overall score.

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 mentions required authentication scope and tells when to use ('understand WHY an agent has a particular score'). However, it does not explicitly state when not to use or mention alternatives among sibling tools.

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 fully compensates by disclosing JWT contents, signing key (Ed25519), authentication scope requirement, example response, and the default for ttl_hours. No contradiction exists.

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 well-structured with a summary, bullet points of JWT contents, parameter details, example, and response format. It is informative but could be slightly more concise by removing some redundancy (e.g., portability statement repeated).

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 3 parameters and no output schema, the description covers purpose, authentication, parameter defaults, and example output. Missing error handling or rate limit info, but overall sufficient for selection and invocation.

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

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

Schema coverage is 0%, but the description adds meaning: agent_id is implied by context, access_token requires specific scope, ttl_hours is validity period with a config-based default. An example call further clarifies usage.

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 issues a signed attestation (JWT) capturing trust scores, specifying verb (issue), resource (signed attestation/JWT), and content. It distinguishes from sibling tools like verify_attestation (which verifies) and list_my_attestations (which lists).

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 explains the attestation is portable for third-party verification without querying the service, and that verifiers can use verify_attestation without authentication. It provides usage context but does not explicitly state when not to use or compare with alternatives like get_agent_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?

No annotations are provided, so the description fully covers behavioral traits: one-time irreversible operation, transfer of history and scores, canonical agent ID contract, authentication change, and detailed error codes.

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 well-structured with sections for purpose, steps, contract, JWT requirements, example, arguments, returns, and errors. While comprehensive, it is lengthy but 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?

Given the complexity (4 params, no output schema, no annotations), the description is thorough: explains parameters, return values, error codes, and behavioral implications. An AI agent can correctly invoke the tool.

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

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

The description adds substantial meaning beyond the schema, including detailed explanations for each parameter, JWT claims requirements, and a Python example. This compensates for the 0% schema description coverage.

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

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

The description clearly states 'Link a standalone trust profile to an AgentAuth identity,' specifying the verb and resource. It distinguishes this tool from siblings by its unique linking operation.

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

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

The description provides clear context for use, including that it is one-time and irreversible, and explicitly explains the dry-run option. It lacks explicit alternatives or when-not-to-use statements, but the context is sufficient.

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 explains that only non-expired, non-revoked attestations are returned, provides example response fields, and notes authentication needs. It does not explicitly state it is read-only, but is strongly implied.

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

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

The description is concise, front-loaded with purpose, and includes a clear example call and response without extraneous 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 simple list tool with two parameters and no output schema, the description provides a full example response and covers authentication and result semantics, making it complete.

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

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

The schema has 0% description coverage, but the description compensates by stating that authentication requires at least one of access_token or public_key_hex. However, it does not elaborate on parameter formats or generation.

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 verb 'list' and the resource 'your active attestations', and distinguishes it from siblings like issue_attestation and verify_attestation.

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 specifies the context (listing one's own active attestations) and authentication requirement, but does not explicitly mention when not to use it or compare with alternatives.

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, but description fully discloses authentication requirements, effect of confirmation, parameter constraints, and example response with structure.

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?

Well-structured with purpose, context, requirements, params, and example. Slightly long example but informative. No wasted sentences.

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, but example response covers all fields. Describes authentication, parameters, and downstream use. Complete for a list 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 0%, but description explains access_token as auth, since_days and limit with defaults/max, plus example usage. Adds significant meaning beyond 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?

Clearly states it lists interactions reported by counterparties awaiting confirmation, with specific verb and resource. Distinct from siblings like confirm_interaction or report_interaction.

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?

Provides context about when to use (after counterparty reports) and hints at alternative (confirm_interaction). Mentions authentication scope. Lacks explicit exclusions but sufficient.

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 full burden and delivers comprehensive behavioral details: registration paths, idempotency, scope limitations, key generation warnings, and the one-time display of private keys. All important traits are disclosed.

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 well-structured with sections, bullet points, and examples. While slightly lengthy, every sentence adds value for a complex tool with multiple modes. The front-loading of purpose and paths aids quick understanding.

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 complexity (5 optional params, 3 registration paths, no output schema), the description is remarkably complete. It details return values, scopes, and provides an example response, ensuring the agent understands all outputs.

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?

Despite 0% schema description coverage, the description thoroughly explains each parameter's meaning, conditions (e.g., mutual exclusivity of access_token and public_key_hex), and provides example calls. It fully compensates 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 clearly states the tool's purpose: registering a new agent in the trust network. It outlines three specific registration paths, making it distinct from sibling tools which focus on queries, trust checks, and interactions.

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

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

The description provides explicit guidance on when to use each registration path, highlighting AgentAuth as preferred and explaining standalone vs. auto-generated keys. It also mentions idempotency and future linking, though it does not explicitly state when not to use the 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 provided, the description fully discloses behavioral traits: identity recording, authentication requirements, the non-destructive nature of the report, storage of context as-is, injection detection, and the mutually_confirmed return logic. This exceeds the minimum needed.

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 well-structured with clear sections (purpose, requirements, options, authentication, returns, example) and every sentence adds value. It is slightly verbose but not wasteful; front-loading the purpose helps quick understanding.

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 and output schema, the description is remarkably complete: it covers all parameters, authentication, return values, example response, injection warnings, credibility guidance, and scope requirements. No critical information 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 0%, so the description must compensate. It lists interaction_type and outcome options, describes context fields (amount, task_type, duration_ms, sla_met), notes evidence_hash is SHA-256, and explains access_token sources (AgentAuth or generate_agent_token). It adds meaning beyond the bare schema, though it could detail counterparty_id further.

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

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

The description clearly states the tool's purpose: 'Report the outcome of an interaction with another agent.' It specifies the verb (report), resource (interaction outcome), and enumerates concrete interaction_type and outcome options, making the function unambiguous.

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

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

The description provides explicit usage guidelines: authentication is required, both parties should report for credibility, and the trust.report scope is needed. It also warns about context injection and explains authentication methods. However, it does not explicitly differentiate from sibling tools like confirm_interaction or file_dispute.

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 fully discloses behavioral traits: the authorization process, side effects of each resolution option (penalties), and that it returns updated status. No contradictions.

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 well-structured with a summary sentence, bulleted auth steps, and list of options. It is slightly verbose on auth details but every sentence adds value. Front-loading is good.

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, the description mentions return of updated dispute status and resolution. It covers resolution options and auth, but could elaborate on error conditions or prerequisites like the dispute being open (already mentioned). Still 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?

Schema coverage is 0%, so description must compensate. It explains the 'resolution' parameter via options (upheld, dismissed, split) and clarifies 'access_token' usage. However, 'dispute_id' and 'resolution_note' lack explicit description, though their purpose is easily inferred.

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

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

The description clearly states the tool's purpose: 'Resolve an open dispute.' It specifies the verb (resolve) and resource (dispute), distinct from sibling 'file_dispute' which would create a dispute.

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 requires arbitrator authorization and details the auth flow, but it does not directly compare to alternatives or specify when not to use it. However, the resolution options and auth requirements provide clear 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?

No annotations provided, so description carries full burden. It details filtering, ranking, and return structure, but omits rate limits or authentication requirements beyond optional token.

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?

Well-structured with Description, Args, and Returns sections, front-loading main purpose. Some verbosity in parameter descriptions, but overall efficient.

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 6 parameters and no output schema or annotations, the description covers input semantics, return structure, and usage context. Lacks pagination details, but limit parameter addresses this.

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 has 0% description coverage; the description compensates fully with detailed Args for each parameter, including ranges, allowed values, and defaults.

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 'Search for agents meeting trust criteria' with specific filters (score, capabilities, interactions) and result ranking, distinguishing it from siblings like check_trust or compare_agents.

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 'Use this to find trustworthy agents for a specific task type' and explains default behaviors for parameters, but lacks explicit when-not-to-use or mention of sibling alternatives.

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 full burden. It details the three detection patterns, describes the return format (risk_score 0.0-1.0, is_suspicious flag, signals), and gives an example response. It does not explicitly state read-only behavior but implies it.

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

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

The description is concise and well-structured: purpose statement, list of detection patterns, summary of output format, and example call/response. No unnecessary 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?

Given the low complexity (single parameter, no output schema), the description is complete. It explains what the tool detects, what it returns, and provides an example. No information 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 description coverage is 0%, but the description compensates by providing a concrete example of the agent_id parameter with a UUID format. It adds value beyond the schema's type and title.

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

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

The description clearly states the tool's purpose: 'Run sybil detection checks against an agent' and lists three specific suspicious patterns. This distinguishes it from siblings like check_trust and check_trust_batch, which focus on trust scores.

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

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

The description provides context by stating 'No authentication required — this is a public safety tool.' It includes an example call, but does not explicitly state when not to use this tool or compare it to alternatives.

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 full burden. It discloses return values (validity status, score snapshot, agent_id, time remaining) and the stateless nature. Could mention error handling or if any side effects exist, but overall good.

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 followed by a list of return fields. No fluff, information is front-loaded. 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?

For a simple 1-parameter tool with no output schema, the description explains all relevant aspects: purpose, return values, and authentication requirements. Complete and sufficient.

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 detail about the jwt_token parameter beyond its name. It does not specify expected format, length, or encoding, leaving the agent to infer.

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 action (verify signature, check expiry, confirm not revoked) and resource (attestation). It distinguishes from siblings like 'check_trust' by focusing on attestation-specific 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?

Explicitly states 'No authentication required' and that attestations are portable and verifiable by any party offline. This tells agents when to use it and that it requires no service-dependent authorization.

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?

Describes all validation steps (token authenticity, key lookup, proof signature, expiry, already linked) and explains that no changes are persisted. With no annotations, the description fully carries the behavioral burden.

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?

Well-structured with overview, Args, and Returns sections; every sentence is informative and no extraneous content.

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?

Comprehensively explains the return value (dict with valid, checks, agent_id, error), compensating for the lack of an output schema and covering all necessary behavioral details.

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%, but the description provides detailed parameter explanations (e.g., 'AgentAuth bearer token', 'Hex-encoded Ed25519 public key'), adding essential meaning beyond the schema's bare titles and types.

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?

Clearly states the tool is a preflight check for validating a link_agentauth proof without writing to the DB, distinguishing it from the sibling tool link_agentauth.

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 before calling link_agentauth', providing clear context for when to use this tool versus the actual linking 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?

No annotations provided, so the description carries full burden. It details the return fields and explains the canonical agent ID contract for linked profiles. No side effects mentioned, but likely none. Auth requirements are implicit from parameters.

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 well-structured with paragraphs and a bullet list of returns. It is front-loaded with the main purpose. Slightly lengthy but each part 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 no output schema, the description includes a detailed list of return fields. It covers the tool's functionality well. Could mention error scenarios, but not necessary for a simple identity check.

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 has 0% description coverage, but the description adds meaningful detail: 'access_token: AgentAuth bearer token' and 'public_key_hex: Hex-encoded Ed25519 public key (standalone agents).' This goes beyond the schema titles.

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 'Check your identity as AgentTrust sees it' and lists the returned fields, making the tool's purpose immediately obvious. It distinguishes itself from sibling tools like 'get_agent_profile' and 'check_trust' by focusing on the caller's own identity.

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 'Useful for verifying your auth is working correctly before making other calls,' which provides clear context for when to use. Does not mention alternatives or when not to use, but for a simple identity check this is sufficient.

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