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

With no annotations, the description carries full burden and discloses almost nothing beyond 'sign'. It doesn't say whether the token is stored or returned, what the default expiry is, what identity/authentication is needed, or whether the operation is idempotent — all critical for a token-minting mutation.

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 sentence with no padding, but it is under-specified rather than concise given the tool's four-parameter surface. The core action is front-loaded, which is a plus.

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 mutation tool with no annotations, no output schema, and completely undocumented parameters, the description is far too thin. An agent cannot tell what a successful call yields (token string? invite URL?) or how the invite relates to owner identity and expiry.

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% across four parameters (name, agentDid, relayUrl, expiresInSeconds) and the description explains none of them. It doesn't even clarify that relayUrl is mandatory or what expiresInSeconds defaults to, leaving every argument to be guessed from its name.

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 has a concrete verb ('Sign') and resource ('acp-invite token') scoped to 'this server owner', so the operation is identifiable. However, it doesn't distinguish this from siblings like acp_revoke_token or acp_delegate_task, and the name/description framing ('create_invite' vs 'sign a token') leaves mild ambiguity about whether it creates, persists, or merely signs.

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

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

No indication of when an agent should call this versus acp_revoke_token or the delegate tools, and no prerequisites such as required identity, permissions, or whether an invite must later be revoked. The only contextual hint is 'for this server owner', which does not guide tool selection.

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. It discloses the outcome distinction between race and quorum, but says nothing about permissions, side effects, budget consumption, isolation requirements, failure behavior, or how relayUrl and outputSchema affect execution.

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 three short, front-loaded sentences with no filler. The purpose comes first and the mode behavior follows immediately, so every sentence earns its place.

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

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

For a complex tool with 10 parameters, nested objects, no annotations, and no output schema, the description is far too thin. It gives a useful high-level purpose and mode outcomes, but an agent still lacks the parameter and operational context needed to invoke it reliably.

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% across 10 parameters, including nested objects and an enum. The description only partly clarifies the mode values and leaves workers, input, budget, relayUrl, quorumSize, outputSchema, minimumIsolationLevel, and the rest 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 gives a specific verb and resource: 'Delegate one task to several workers.' It also clarifies the two mode outcomes, which helps distinguish the tool from a single-worker delegate sibling. It stops short of explicitly naming the sibling or contrasting its scope, so it is clear but not fully differentiated.

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

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

The phrase 'one task to several workers' implies when this tool applies, and the race/quorum result semantics add some guidance. However, it does not say when to choose race versus quorum, when to use acp_delegate_task instead, or what exclusions or prerequisites exist.

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. It mentions verified output and an audit summary, but omits side effects, budget handling, auth or invite requirements, isolation behavior, and whether execution is synchronous or asynchronous.

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 or redundancy. It is appropriately terse, though its brevity contributes to the broader under-specification problem.

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 nine parameters, nested objects, no annotations, and no output schema, the description is far too thin for the tool's complexity. It gives a high-level outcome but leaves an agent unable to call the tool correctly without guessing about most inputs.

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 across nine parameters, and the tool description explains none of them. Critical inputs such as budget, relayUrl, workerDid, inviteToken, outputSchema, and minimumIsolationLevel are left entirely undefined.

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 has a specific verb and resource: delegate one task to an ACP worker. It also states the return value (verified deliverable plus audit summary). The word 'one' implicitly contrasts with acp_delegate_multi, but that sibling is not named explicitly.

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, when-not-to-use, prerequisite, or alternative guidance. The single-task phrasing weakly implies that acp_delegate_multi is for multiple tasks, but the agent must infer this rather than being told.

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 implies a mutation ('record it') and cryptographic signing ('sign'), but says nothing about required keys or permissions, whether revocation is reversible, what happens to existing records, or what the response contains. This is a significant gap for a mutation 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?

A single efficient sentence with no filler. It is front-loaded and appropriately sized, though its brevity comes at the cost of the missing information noted in other dimensions.

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-required-parameter mutation with no annotations, no output schema, and 0% parameter documentation, the description is far too thin. An agent would not know what is being revoked, what the enum targets mean, or what signing entails.

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% across three required parameters. The description does not explain 'reason', 'targetId', or the critical enum distinction between 'invite' and 'capability' in 'targetType', so it does not compensate for the missing schema documentation.

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 (sign a RevocationNotice and record it in this server registry), which is more informative than the tool name alone. However it never clarifies that revocation is for invites or capabilities, so the enum-selected target is a surprise relative to the 'revoke_token' name. It does not distinguish itself from siblings like acp_create_invite or acp_verify_audit_bundle.

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 sibling tools (e.g. acp_create_invite or acp_verify_audit_bundle). No prerequisites, no when-not-to-use, and no mention of an alternative are provided.

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

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

With no annotations, the description carries the whole burden, and it only states that a report is returned. It does not say whether the call is read-only, whether an invalid bundle raises an error or returns a negative report, whether a trust anchor is required, or any auth/rate constraints.

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 efficient, front-loaded sentence with no filler. Brevity is appropriate, though it edges into under-specification given the complexity of the inputs.

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 nested object inputs, zero schema coverage, no output schema, and no annotations, one sentence is not enough. The meaning of 'bilateral', the role of 'anchor', and the shape/interpretation of the verification report are all left to inference.

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% and both parameters are nested objects with no field descriptions. The description only implies the 'bundle' parameter; the optional 'anchor' parameter — likely a trust anchor that materially changes verification behavior — is never mentioned, so the agent has no basis for deciding whether to supply it.

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

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

States a specific verb and resource ('Verify a bilateral AuditBundle') plus the return ('verification report'), which clearly separates it from the sibling tools (revoke/delegate/invite). The 'bilateral' qualifier is unexplained, so the agent knows the operation class but not exactly what is being validated.

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 versus alternatives, no prerequisites (e.g. must the bundle come from a counterparty?), and no indication of what to do on failure. The siblings are unrelated enough that disambiguation is low-risk, but no usage context is supplied at all.

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