Free Agent Economy Lab

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral details about the gates used (audit, risk, liquidity, etc.) and reinforces that no funds are moved. This provides context beyond the annotations.

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, no redundancy, front-loaded with the core action. 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 7 parameters with no schema descriptions, no output schema, the description lacks detail on return value and parameter constraints. It covers the high-level goal but misses specifics that would help an agent use 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?

With schema description coverage at 0%, the description should compensate. It mentions capital_usd and venues by inference, but does not explain the purpose of max_risk_score, max_credible_apy, max_per_venue_pct, max_withdrawal_days, or annual_operating_cost_usd. So only minimal parameter context is provided.

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 uses 'Allocate paper capital across 1-10 caller-supplied yield venues' which clearly indicates the tool's function as a simulation allocator. It also notes 'Never moves funds' to distinguish from real transfers. Siblings include compare_providers and verify_outcome, so this is distinct.

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 it is for allocation simulation with user-supplied venues, but does not explicitly state when to use it versus compare_providers or verify_outcome. No exclusions or alternatives 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so behavioral profile is clear. Description adds the sparse-sample penalty detail, which provides extra context beyond annotations.

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?

Single sentence that is front-loaded with the main purpose and criteria. No redundant 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 tool has 2 parameters, no output schema, and rich annotations, the description explains the ranking logic adequately. However, it does not specify the return format or additional behavior.

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 hints at 'supplied outcome receipts' for receipts parameter and 'sparse-sample penalty' for minimum_samples, but does not fully describe each parameter's meaning or constraints.

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?

Description clearly states the verb 'rank', resource 'providers from outcome receipts', and criteria including success, quality, cost, and sparse-sample penalty. Differentiates from unrelated siblings (allocate_treasury_paper and verify_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?

Implied usage from description (ranking providers based on receipts) but does not explicitly state when to use or when not, nor reference alternative 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is clear. The description adds value by specifying the criteria checked (delivery, spend, quality), which is beyond the annotations. However, it does not disclose the output format 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?

The description is a single sentence of 14 words, with no wasted words. It is front-loaded with the verb ('Check whether'), immediately conveying the tool's purpose. 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?

Given the tool's simplicity (one parameter, no output schema) and good annotations, the description is minimally adequate. It states the verification criteria but lacks details on the receipt object structure and return value. For a complete understanding, the agent may need external knowledge of the receipt 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?

The schema has 0% description coverage and only defines a required 'receipt' object with no properties. The description provides minimal context by naming the receipt type ('agent-outcome-receipt/0.1'), but it does not explain the object's structure or expected fields, leaving the agent with insufficient information to correctly populate the 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 a supplied receipt against recorded delivery, spend, and quality requirements. It specifies the resource ('agent-outcome-receipt/0.1') and the verb ('check'), making the purpose unambiguous. The sibling tools (allocate_treasury_paper, compare_providers) are unrelated, so no confusion.

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 when you have an outcome receipt to verify, but it does not provide explicit guidance on when to use or avoid this tool, nor does it mention alternatives. The context is implied but not explicitly stated.

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