GovOmniAI Machine Services

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

With no annotations, the description carries the full disclosure burden. It does disclose meaningful non-behaviors: it does not submit bids, contact the Government, make certifications, or create payment, and it restricts inputs to public/buyer-authorized non-sensitive information. However, it does not describe side effects, data persistence, authorization mechanics, or what the tool actually does beyond 'run' a preview.

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. The first sentence front-loads the action and data constraint; the second efficiently clarifies the tool's non-actions. Every sentence serves a purpose, and the length is appropriate for the content conveyed.

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?

The tool has 4 parameters, two deeply nested objects, zero schema descriptions, no output schema, and no annotations – a complex invocation surface. The description does not explain how to construct the nested objects, what the expected result format is, or what the qualifier preview actually evaluates. An agent cannot reliably call this tool correctly based solely on this text.

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%, and the description adds no parameter-level meaning. It does not explain 'opportunity', 'company_profile', 'pursuit_role', or 'buyer_reference' – their purpose, structure, or constraints. The only input hint is 'non-sensitive information', which is too generic to guide construction of the nested objects.

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 a specific verb ('Run') and names the exact resource ('Cropper Industries Federal Opportunity Qualifier shadow preview'), making the tool's identity clear. It also distinguishes it from siblings by emphasizing that it is a preview and listing actions it does not take. However, it never explicitly states that the tool assesses or qualifies an opportunity against a company profile, leaning on the tool name for that core meaning.

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 its siblings ('govomniai_transaction_assurance_shadow', 'list_machine_services') or when not to use it. The phrase 'free ... shadow preview' hints at a non-production use case, but no decision rule or alternative selection criterion is 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 present, the description carries the full burden of behavioral disclosure. It explicitly discloses the tool's non-mutating nature—no order creation, no payment request, no transaction authorization—and notes that inputs are caller-declared rather than independently verified. However, it does not disclose what the evaluation returns or whether there are any rate limits or authentication requirements.

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 deliver the tool's purpose, scope, and side-effect profile with no filler. The safety disclaimer is front-loaded and the description is economically structured.

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?

The tool has a nested input schema, three top-level parameters, no output schema, and no annotations, so the description must do more than it does. It fails to describe what the preview returns, how the evaluation is presented, or how an agent should interpret the result. This is a significant completeness gap for a tool an agent must invoke and react to.

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 only 33%, so the description should compensate for undocumented parameters. It adds the high-level semantic that both transaction and evidence inputs are caller-declared, but it does not explain individual fields such as buyer_reference or transaction. The schema's nested enums and the evidence value list carry most of the parameter meaning, making this adequate but not thorough.

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 a specific verb and resource: 'Run the free GovOmniAI Transaction Assurance shadow preview.' It clearly states the tool's job—evaluating caller-declared transaction risk and evidence sufficiency—and works to distinguish itself from a real transaction by naming what it does NOT do. This prevents confusion with any execution-style transaction tools.

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 establishes clear usage context: it is a 'free shadow preview' that 'creates no order, requests no payment, and authorizes no transaction,' signaling this is a safe, non-committal evaluation step. It does not explicitly name alternatives or state exact when-not-to-use conditions, but the context is strong enough for an agent to infer appropriate use.

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. It does disclose the key safety-relevant behavior: discovery only, no order or payment. However, it does not mention any other behavioral traits such as authentication requirements, result size, or pagination, though the zero-parameter nature reduces the need for deeper disclosure.

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 compact sentences with no redundant wording. The primary listing purpose is front-loaded, and the clarifying non-transactional statement is placed directly after it, earning its place by preventing misuse.

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 zero-parameter discovery tool with no output schema, the description provides enough context to understand what the tool returns conceptually (machine services and legal sellers) and what it does not do (create orders/payments). It could mention result format or availability constraints, but these are minor gaps given 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 input schema has zero parameters and 100% schema description coverage, so there is no parameter burden for the description to carry. Per the baseline for zero-parameter tools, a 4 is appropriate; no additional parameter documentation is needed.

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 a specific verb ('List') and a clear resource ('GovOmniAI machine services and legal sellers'), making the tool's purpose immediately obvious. It also explicitly contrasts with order/payment behavior, which helps distinguish it from the sibling transaction-related tools despite their opaque names.

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 'This is discovery only and does not create an order or payment' gives clear usage context and an explicit exclusion: it should not be used for transactional actions. It does not name alternative tools directly, but the behavioral boundary is strong enough to guide correct selection.

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