AgentWork Outcomes

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

With no annotations provided, the description carries the full burden of disclosing side effects. It explicitly warns 'This may cause a financial action when funding is enabled', which is a material behavioral disclosure beyond what the title implies.

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

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

Two sentences with no filler: the action is front-loaded and the financial warning follows immediately. Every word contributes useful meaning.

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

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

For a single-parameter confirmation tool, the description covers the core action, the precondition, and the key risk. It does not detail error behavior or explicitly route among siblings, but those are minor gaps relative to the tool's simplicity.

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 provides no description for quote_id and schema coverage is 0%. The description partially compensates by referring to a 'previously returned quote', implying that quote_id comes from an earlier response, but it never explicitly ties the parameter to that origin or explains its format.

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 and resource: 'confirm a previously returned quote'. It also clarifies the consequential purpose, 'begin configured funding', which distinguishes it from siblings like get_outcome, request_outcome, and resume_outcome.

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 'previously returned quote' establishes the expected precondition: this tool follows a quote-generation step. It clearly implies the right moment to call it, though it does not explicitly name alternatives 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 carries the full burden. 'Read' and 'current state' convey a non-mutating retrieval, and the scope is explicit. However, it omits error behavior, whether an outcome must already exist, and any access or prerequisite details.

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

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

The description is a single, front-loaded sentence beginning with the operative verb 'Read'. It lists the relevant state dimensions without filler or 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?

For a one-parameter read tool, the description names the operation and the state dimensions returned. Still, with no annotations and no output schema, it leaves ambiguity about response shape, not-found behavior, and whether any preconditions apply.

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 refers to 'an outcome' without explaining outcome_id format, constraints, or usage. It adds little meaning beyond the schema's property name and type.

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 a read operation on an outcome's current state and enumerates the exact scope: payment, supplier, artifact, verification, and remediation. This effectively distinguishes it from the action-oriented siblings confirm_outcome, request_outcome, and resume_outcome.

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 guidance is provided on when to use this tool versus the sibling tools. The sibling names imply they perform actions, but the description never states whether get_outcome should be used first, for preconditions, or after modifications.

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 behavioral burden. It clearly discloses that the tool does not spend, post, purchase, or invoke anything, and that it returns a single quote. It does not mention potential persistence/recording side effects or failure behavior, but the most important non-execution trait is explicit.

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 tight sentences with no filler. The first sentence front-loads the primary purpose, and the second sentence adds a crucial non-execution warning. Every word 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 8-parameter tool with a oneOf schema and no output schema, the description gives sufficient high-level orientation: it plans an outcome and returns one quote without executing. The schema covers parameter details, so the description does not need to repeat them. It lacks explicit guidance on choosing between outcome, retry_gap_id, and repeat_of_outcome_id, but those are described in the schema.

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

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

Schema description coverage is 100%, so the schema already documents all eight parameters. The description adds minimal semantic value beyond the schema, only restating the outcome concept in natural language. Baseline 3 is appropriate.

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+resource: it finds a reliable procurement plan and returns one retail quote. It also explicitly distinguishes itself from execution tools by stating 'does not spend, post, purchase, or invoke anything', which separates it from confirm_outcome and similar actions.

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 when to use this tool by noting the output is 'for confirmation', suggesting confirm_outcome as the next step. However, it does not explicitly name alternatives or state when not to use this tool versus get_outcome, resume_outcome, or confirm_outcome.

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

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

With no annotations, the description carries the full burden, and it does disclose an important behavioral trait: idempotency, which tells agents that repeated calls are safe. However, it does not clarify whether reconciliation has side effects, what the response looks like, or what prerequisites or permissions are 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 a single, front-loaded sentence that wastes no words. It places the key behavioral term 'Idempotently' first and conveys the core operation compactly.

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 one simple parameter and no output schema, the description gives a reasonable starting point by stating the operation and the domain. It is incomplete, though, because it leaves usage timing, side effects, and return behavior unspecified, and there are no annotations to fill those gaps.

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 undocumented `outcome_id` parameter. It only references 'an outcome' generically and never explicitly explains that `outcome_id` is the identifier of the outcome being resumed, nor its format or required semantics.

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 specific action ('Idempotently poll or reconcile') and a resource ('pending supplier and financial operations for an outcome'), which distinguishes it from the sibling tools that request, get, or confirm outcomes. However, the phrase 'poll or reconcile' is slightly ambiguous about whether these are alternative modes or intertwined steps.

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 word 'pending' implies this tool is for handling outcomes that have unfinished supplier or financial operations, giving some context for when to use it. It does not explicitly say when not to use it or name any alternative, so usage guidance is only implied rather than stated.

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