Tool-Call Origin Attestation

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

No annotations are provided, so the description carries the full burden of behavioral disclosure, yet it only describes billing. It does not state what the check validates, whether it is read-only or mutating, what permissions are required, or what happens on failure.

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 short and front-loaded, but it is under-specified rather than concise. Important context is missing, and the billing parenthetical takes space that could have been used to explain the operation.

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 nested object parameters, no output schema, no annotations, and 0% schema description coverage, the description is grossly incomplete. An agent cannot confidently determine what the tool does or how to invoke it correctly.

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

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

The schema has 0% description coverage and two parameters, one of which is a required nested object. The description merely echoes the parameter names '{execution, attestation}' without explaining their meaning, expected structure, or role.

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 restates the tool name as 'Attestation check' and lists parameter names in braces, but never explains what an attestation check actually does or how it differs from siblings like probe or verdict_lookup. It is near-tautological rather than a clear verb+resource statement.

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 mentions billing options ('$0.01 x402 / bundle / fleet included') but gives no guidance on when to use this tool, when not to use it, or which sibling tool is the alternative. The agent is left to infer usage entirely.

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, so the description carries the full behavioral burden. It does disclose one meaningful trait (conditional execution on attestation), but leaves critical questions unanswered: what happens when not attested (error, no-op, rejection), whether this mutates or destroys state, what permissions are needed, and what is returned.

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

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

One short, front-loaded fragment with no filler. However, the brevity here reflects under-specification rather than disciplined conciseness, so it earns only a middling score.

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?

A tool taking two nested object parameters, with no annotations, no output schema, and no field-level documentation anywhere, is described by a single cryptic clause. An agent has essentially nothing to work with to invoke this correctly, making the description wholly inadequate for the tool's complexity.

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

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

Both parameters are nested objects at 0% schema description coverage, so the description must compensate. Instead it merely repeats the schema property names ('execution', 'attestation') with no explanation of their expected shape, required fields, or the relationship between them. Near-zero added value for two opaque object 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?

States a verb ('dispatch') and names the two inputs, plus a gating condition ('executes ONLY on ATTESTED'). However, 'PEP' and 'ATTESTED' are undefined internal jargon, so an agent cannot confidently tell what the tool actually performs or how it differs from siblings like attestation_check. The purpose is gestured at but not concretely stated.

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 only usage-relevant information is the precondition that execution happens only when attested, and even that term is unexplained. There is no guidance on when to call this versus attestation_check, verdict_lookup, or probe, and no statement of required prerequisites or sequencing.

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 discloses a cost model, but says nothing about whether the probe is read-only, what it returns, permissions required, side effects, rate limits, or failure 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 very short but cryptic and under-specified; field names and pricing are packed into one line while essential invocation context is missing. Brevity here reflects omission rather than well-structured conciseness.

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 required parameters, no annotations, no output schema, and 0% schema description coverage, the description is almost entirely inadequate. It does not explain what 'forged-shape' means, what target_mode is, what the tool returns, or what an agent needs in order to call it correctly.

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

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

Schema description coverage is 0%, so the description must explain parameter meanings, but it only repeats parameter names in braces. It also mentions target_mode, which is absent from the schema, adding confusion rather than semantic clarity.

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 names a 'Forged-shape probe suite' and lists field names, but gives no clear action verb or explanation of what probing actually does. It does not distinguish this tool from siblings such as attestation_check or verdict_lookup.

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

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

There is no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. The only usage-adjacent information is pricing ('$4.99 / first free per operator ever'), which does not help an agent choose between 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?

No annotations are provided, so the description carries the full burden, and it discloses nothing about side effects, auth requirements, scope of 'own', or whether it is a read or a state change. The word 'validity' hints at a check but never states what is validated or against what.

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?

At five words it is short, but this is under-specification rather than conciseness: the fragment lacks a verb and gives the agent nothing front-loaded to act on. Every word is technically wasted because none resolve what the tool actually does.

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

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

With no annotations, no output schema, and a fragmentary description, an agent cannot determine what this tool returns or when it applies. For a zero-parameter tool in a six-tool family, the definition is far too thin to support correct selection or 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?

The tool takes zero parameters, so per the rubric this is a baseline 4. The description does not need to compensate for any parameter documentation gap.

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

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

The phrase 'Own receipt chain + validity' names a resource (receipt chain) and an attribute (validity) but supplies no verb, so it is unclear whether the tool fetches, lists, verifies, or mutates receipts. It also fails to distinguish itself from nearby siblings like attestation_check and verdict_lookup, which plausibly cover overlapping validity-checking territory.

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

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

There is no indication of when to call this tool, what precondition triggers it, or how it differs from attestation_check, verdict_lookup, or probe. An agent has no basis for choosing between these five 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, the description carries the full behavioral burden, and it partially meets it by disclosing the 409 response on re-registration — concrete, non-obvious error behavior. It omits permission/auth requirements, whether the operation is idempotent beyond the 409, and what a successful registration returns or changes.

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

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

A single compact sentence with the operation front-loaded and the notable error behavior trailing it; no filler or repetition. It is efficient, though the extreme brevity is closer to under-specification than to tight writing.

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 three-parameter mutation tool with no annotations, no output schema, and 0% schema coverage, the description is too thin: it supplies neither parameter meaning nor auth context nor a description of the result. The 409 note is the only substantive detail beyond the bare operation name.

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, and it does not: it merely restates the three parameter names in braces without explaining the format of issuer_id or public_key (e.g. key encoding) or the permitted values of issuer_class. An agent learns nothing about the parameters beyond their existence and requiredness.

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+resource ('Register an issuer') and enumerates the payload fields, so the operation is unambiguous. It does not differentiate from siblings, but none of them (attestation_check, dispatch, probe, receipts, verdict_lookup) overlap with registration, so there is nothing to distinguish.

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 statement of when to call this versus other tools, no prerequisites, and no mention of authorization or registration-order requirements. The only usage-relevant hint is the 409 duplicate case, which is a failure mode rather than 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?

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: not whether this is a read-only lookup, whether it requires auth or an issuer registration, whether it errors on unknown keys, or what a verdict contains. 'Verdict' hints at a read but the description never states 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 single fragment contains no filler, but it is drastically under-sized for a four-required-parameter lookup. Brevity here reflects missing information rather than efficient structure.

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?

A tool with four required, undocumented parameters, no annotations, no enums, and no output schema needs the description to explain key formats and return shape; instead it supplies one bracketed fragment. Nothing an agent needs in order to call it correctly is present.

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 description coverage, the description must compensate and does not. It lists the four parameter names but supplies no format, allowed values, or meaning — critically, 'patch_state' could be a boolean, enum, or free string and 'surface' is entirely opaque.

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 fragment 'Verdict by {framework, version, patch_state, surface}' names a resource and its lookup key but no verb or scope, so it reads as a restatement of the tool name plus its required inputs. It gives no basis for distinguishing this from siblings like attestation_check or probe.

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 call this tool, when not to, or which sibling to prefer (attestation_check, probe, receipts, dispatch). The agent must guess from the name alone.

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