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

With no annotations, the description carries the behavioral disclosure burden. It does disclose that the operation appends a check and that trusted-origin callers must supply ingest_attestation, adding some auth-related context. However, it does not explain side effects, immutability, failure behavior, or whether existing data is modified beyond the append.

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 sentences with the core action front-loaded and no filler. The only minor issue is the unexplained term 'Trusted origin,' which could confuse an agent.

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

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

For a tool with four parameters, a nested object, no output schema, and no annotations, the description is too thin. It omits key guidance on proposition_id/view_id semantics, the shape of check, when to use the tool, and what happens after the append, leaving an agent under-informed for reliable 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 description coverage is 0%, so the description must compensate, but it only alludes to 'check' and 'ingest_attestation.' It does not clarify the roles of proposition_id, view_id, the structure of the check object, or how ingest_attestation relates to authorization.

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: 'Append a VerificationCheck to a stored view.' This clearly indicates a state-changing operation and is distinct enough from siblings like ewp_evidence_view_get. However, 'VerificationCheck' and 'stored view' are domain-specific and not fully disambiguated from ewp_evidence_view_put or ewp_evidence_record.

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 no explicit when-to-use guidance or alternatives. The phrase 'Trusted origin requires ingest_attestation' is a useful precondition, but it does not explain when to choose this tool over sibling tools such as ewp_evidence_record or ewp_evidence_view_put.

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 bears the full burden of disclosing behavioral traits. It mentions 'Append', implying a mutation, but provides no details on side effects, idempotency, required permissions, or return behavior. This is insufficient for a write operation.

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

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

The description is a single sentence with no fluff, which is structurally concise. However, it is under-specified—it sacrifices necessary detail for brevity, making it minimally useful. It is better than a pure tautology but nowhere near the informative level needed.

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 4 parameters including a nested object, no annotations, and no output schema, a one-line description is wholly inadequate. It fails to explain the purpose of the stored view, the structure of EvidenceItem, or the meaning of ingest_attestation. An agent cannot call this tool correctly based solely on this description.

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

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

Schema description coverage is 0%, so the description must compensate for parameter documentation. It does not mention any parameters (proposition_id, evidence, text, ingest_attestation) or their roles. This adds no value 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?

The description states a specific verb ('Append') and resource ('EvidenceItem to a stored view'), which clearly indicates an add operation. However, it does not differentiate from sibling tools like ewp_evidence_view_put or ewp_check_record, leaving ambiguity about what a 'stored view' is and how this tool differs from similar ones.

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 no context about when to use this tool versus alternatives. It does not mention prerequisites, typical scenarios, or exclusions. An agent is left without guidance on selecting this tool over siblings.

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. 'Load' implies a read-only retrieval, but the description does not state whether the operation is safe, what it returns, whether it errors if the view is missing, or any side effects. For a tool with zero annotation coverage, this is a significant transparency gap.

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

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

The description is a single, front-loaded sentence with no filler words. It communicates the essential resource and lookup key efficiently.

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 two-parameter retrieval tool with no output schema, the description should at least indicate what gets returned or what distinguishes this from sibling tools. It only says that a stored EvidenceView is loaded, leaving the agent without enough information about invocation success, return value, or when to use it. The absence of annotations makes this gap more significant.

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 for the schema's lack of explanations. It does clarify that proposition_id is the key used for loading, but it leaves view_id entirely unexplained, including when it should be supplied and how it relates to proposition_id.

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

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

The description states a clear verb ('Load') and resource ('a stored EvidenceView'), and it specifies the lookup key ('by proposition_id'). It is reasonably specific, but it does not explicitly distinguish itself from the sibling tool ewp_evidence_view_put, leaving some differentiation to be inferred from the name.

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 no guidance on when to use this tool versus alternatives such as ewp_evidence_view_put or ewp_evidence_record. It does not mention preconditions, exclusions, or any decision criteria an agent could use to choose 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 provided, the description carries the full burden. It usefully discloses rejection behavior and a trust-based parameter requirement. Still, it omits side effects (create vs update), error behavior, and response shape for a mutating operation.

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

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

Three short sentences convey the action, an exclusion, and a parameter condition. Every sentence earns its place, and the main purpose is front-loaded.

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 two-parameter tool, the description covers the essential action, a key refusal case, and a parameter requirement. However, the term 'trusted origins' is undefined, and the absence of any output schema or return behavior leaves some ambiguity for an agent deciding whether the call succeeded.

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 add meaning. It partially does: 'view' is clarified as an EvidenceView (not WarrantView), and 'ingest_attestation' is tied to trusted origins. But it does not describe the view object structure or the attestation semantics for non-trusted origins.

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 ('Persist') and resource ('EvidenceView'), making the core operation clear. It also explicitly refuses WarrantView bodies, which differentiates it from warrant-related tools, though it does not explicitly distinguish itself from ewp_evidence_view_get.

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 persisting EvidenceView objects and provides a when-not condition via 'Refuses WarrantView bodies.' It also gives a conditional requirement for trusted origins. However, it does not explicitly name alternatives or say when to prefer a sibling tool like ewp_evidence_view_get.

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. It discloses one behavioral nuance: permission is not inferred from WarrantView alone, which is useful. But it doesn't mention read-only status, side effects, error behavior, or return format. The single behavioral note adds value but leaves significant gaps.

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

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

The description is two sentences with no filler, and the key constraint about not inferring from WarrantView is stated early. It is appropriately short for a simple gate, though the opening phrase 'Separate action gate' is cryptic and could be clearer.

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 5 parameters, no output schema, and no annotations, the description is severely incomplete. It fails to explain what the tool returns, how the optional parameters affect behavior, or what scenario warrants its use beyond the WarrantView distinction. An agent would have difficulty calling it correctly without additional context.

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 by explaining parameter purpose. It only references 'action' and 'WarrantView' (likely the warrant parameter), but says nothing about risk_policy, evaluated_at, or proposition_id. It adds minimal meaning beyond the required property list, failing to clarify how the parameters interact.

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 calls the tool a 'Separate action gate' and mentions an action object, which hints at a permission check, but it never states a clear verb or resource. It distinguishes itself from WarrantView by saying it won't infer permission from that alone, but the core function (e.g., 'check whether an action is permitted') is implied rather than explicit.

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

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

It provides some usage context by stating it requires an action object and will not infer permission from WarrantView alone, implying this tool is for action-level checks rather than just viewing warrants. However, it doesn't name sibling alternatives or give explicit when-to-use vs. when-not-to-use guidance, leaving the agent to infer the decision boundary.

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

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

With no annotations, the description carries the full behavioral burden. It does add some context: the result is bounded, not a biography, and OPEN/DEGRADED states are surfaced. But it never states whether this is a read-only lookup, whether it mutates state, what permissions are needed, how the packet is returned, or what OPEN/DEGRADED actually mean for the caller.

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 text is short and front-loaded, but brevity crosses into under-specification: 'axes,' 'OPEN,' and 'DEGRADED' are unexplained jargon, and the noun-phrase fragments do not form a usable instruction. It is compact, not genuinely 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?

For a tool with four parameters, no parameter descriptions, no annotations, and no output schema, this description leaves most of the call contract implicit. An agent cannot determine what inputs to provide, what output to expect, or how this fits into the ewp workflow, so it is not adequately complete.

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

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

Schema description coverage is 0%, so the description must compensate, but it does not explain any of the four parameters: query, view_id, evaluated_at, or proposition_id. The terms 'axes, evidence ids, warnings' appear to describe the output packet rather than input semantics, leaving an agent to guess how to populate required fields.

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 specifies a concrete resource: a bounded packet containing axes, evidence ids, and warnings, and explicitly excludes 'persona biography,' which gives an agent a distinct conceptual boundary. However, it lacks an explicit verb (e.g., retrieves, stores, computes) and never names a sibling tool it is not, so it stops short of full differentiation.

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

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

There is no guidance on when to invoke this tool versus any of the ewp_* siblings, such as ewp_evidence_view_get or ewp_warrant_now. 'OPEN and DEGRADED are explicit' hints at state semantics but does not state a trigger condition, input prerequisite, or alternative.

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

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

With no annotations, the description carries the burden of behavioral disclosure. It does add useful non-obvious information: the tool returns five normative axes and does not persist the warrant. But it omits other behavioral details such as prerequisites, error conditions, whether it requires a stored view vs inline object, and what happens with conflicting 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 two short sentences with no filler. The core action is front-loaded, the 'does not persist' note is a purposeful behavioral clarification, and every sentence earns its place.

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

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

Given six parameters, 0% schema coverage, no output schema, and no annotations, this description is too sparse to fully support correct invocation. It establishes the main intent and the non-persistence side effect, but leaves most parameter semantics and the expected response shape underspecified.

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 partially does by distinguishing 'inline or stored' EvidenceViews, which roughly maps to view vs view_id, and by tying evaluated_at to the evaluation time. However, policy_id, policy_version, proposition_id, and the relationship between view and view_id are left completely unexplained.

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

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

The description states a specific operation: evaluate an EvidenceView at a point in time, and names the result ('five normative axes'). 'Does not persist warrant' helps separate it from persistence tools. However, it does not explain what the 'five normative axes' are or how this tool relates to siblings like ewp_check_record or ewp_may_act.

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

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

There is no explicit when-to-use or when-not-to-use guidance. The only signal is 'Does not persist warrant,' which hints that this tool is for evaluation rather than storage, but no alternative tool is named and no selection criteria are given.

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