subproof

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

No annotations are provided, so the description carries the full burden. It discloses the output format and content, but does not mention potential size limits, pagination, or whether this is a synchronous export. It is reasonably transparent but lacks deeper behavioral context.

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 states the action, resource, format, and content fields without any unnecessary words. Every element 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 simple export tool with no parameters and no output schema, the description covers the essentials: what you get and in what format. It lacks only minor details like 'request history' semantics, but overall it is complete for effective usage.

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 has zero parameters, so there is no input schema to clarify. The description still adds value by specifying exactly what data will be exported, which is sufficient in the absence of 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?

The description states a specific verb ('Export'), a specific resource ('full subcontractor compliance report'), and the output format ('CSV text') with content details. This clearly distinguishes it from sibling tools that focus on summaries or specific subsets.

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: use this when you need the complete compliance report as CSV. However, it does not explicitly mention when not to use it or compare it to alternatives like get_compliance_summary or search_sub_docs, so guidance remains implicit.

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 disclosing behavioral characteristics. It lists the data returned but does not explicitly state that the operation is read-only, nor does it mention any side effects, permissions, or limitations. The verb 'Get' and absence of parameters suggest a safe read operation, but the description adds only limited behavioral context.

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 efficiently conveys the tool's purpose and the exact categories included in the summary. It contains no redundant phrases or filler, with every word earning 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 simple no-parameter tool without an output schema, the description adequately conveys what the summary contains. It could be slightly more explicit about the format (e.g., counts of subcontractors) but overall it provides sufficient context for an agent to understand the tool's functionality.

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?

This tool has zero parameters, so the input schema is trivially fully covered. According to the rubric, a baseline score of 4 applies when there are no parameters, and the description appropriately avoids adding irrelevant parameter information.

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's function with a specific verb ('Get') and resource ('subcontractor compliance summary'), and enumerates the specific categories included (tracked, not received, lapsed cover, lapsing this week, awaiting check). This distinguishes it from sibling tools like get_expiring_cover and list_uninsured_subs, which focus on narrower subsets.

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 does not explicitly mention when to use this tool versus its alternatives or any exclusions. It implies that it is used to fetch an overall compliance summary, but provides no guidance on choosing it over siblings like export_compliance_report or search_sub_docs.

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 accurately implies a read-only listing operation and adds context about the look-ahead window and default behavior. Yet it does not explicitly confirm there are no side effects, nor does it describe the return format or edge cases (e.g., when no documents expire). This is adequate for a simple list tool but lacks richer detail.

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, front-loaded with the main action and includes the purpose and default. Every word earns its place, with no redundant information. It is highly concise and well-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?

For a single-parameter list tool with no output schema, the description is sufficiently complete. It conveys the primary function, the configurable window, and the business motivation. It does not detail the output structure, but for a list operation this is generally understood. The description covers all essential aspects given its 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 already documents the 'days' parameter with a description, and schema coverage is 100%. The description adds no semantic information beyond what the schema provides, merely using 'N' as a placeholder. The default is already stated in the schema, so the description adds no extra value for parameter understanding.

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 identifies the action ('List subcontractor documents expiring') and the specific scope ('within the next N days'), distinguishing it from sibling tools like list_uninsured_subs (which likely lists subs without coverage) and search_sub_docs (generic document search). It also states the intended purpose, making the tool's role unambiguous.

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 provides clear context for when to use the tool: to renew certificates before coverage lapses. It implies this is for proactive monitoring, and the default 30-day window gives a practical starting point. However, it does not explicitly mention alternatives or situations where it should not be used, which would be helpful given the 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?

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that results are filtered to lapsed/missing documents, that the relevance is immediate liability, and that the list is ordered with 'most dangerous first'—all useful behavioral traits. It does not mention whether it is read-only, but 'List' implies that, and no other side effects are suggested. This adds meaningful context beyond the name.

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, focused sentence (with a dash-emphasized fragment) that efficiently conveys the purpose, the filtering criteria, and the ordering. Every phrase earns its place: 'lapsed or missing insurance documents' defines the scope, 'liability exposure right now' clarifies urgency, and 'Most dangerous first' specifies the sort order. There is no redundancy or filler.

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 no parameters and no output schema, the description sufficiently explains what the tool does, including the criteria and ordering. It does not mention return fields or pagination, but for a simple list tool this is not critical. The sibling tools provide some context, and this description clearly aligns with its name and purpose. It is adequate for an agent to understand the tool's basic behavior, though it could have noted that it only returns subs without valid documents.

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 has zero parameters, so the schema provides no semantic detail. Per the rubric, a 0-parameter tool gets a baseline of 4. The description adds value by explaining what the list contains, but it does not need to elaborate on parameters since none exist.

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 identifies the tool as listing subcontractors with lapsed or missing insurance documents. It specifies the resource (subcontractors), the action (list), and the exact filter (lapsed/missing insurance), which distinguishes it from sibling tools like get_expiring_cover (which handles upcoming expirations) and get_compliance_summary (which likely provides a broader overview).

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 'creating liability exposure right now' establishes clear context for when to use this tool—when immediate risk is the concern. However, it does not explicitly name alternatives or provide when-not-to-use instructions, so it falls short of a perfect score. The context is clear enough that an agent could infer it should be used to identify current uninsured subs rather than future expirations.

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. It discloses the return fields (expiry date and status with enumerated values like 'on file' and 'lapsed'), which is useful. However, it does not explicitly confirm read-only behavior, pagination, or any side effects, though the search semantics imply a safe read-only operation.

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 fluff. It directly states the search action and the output format, and 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 simple tool with one optional parameter and no output schema, the description covers the core behavior and output. It does not mention that omitting the query lists everything, but that is covered in the schema. A brief note about omitting the query in the description would have made it more complete, but the current level is sufficient for this 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?

Schema description coverage is 100%, with the parameter description already covering case-insensitivity and shorthand tokens like 'COI'. The tool description adds no extra parameter meaning beyond the schema, so the baseline score of 3 applies.

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 searches subcontractor documents by sub name or document type, which is a specific verb+resource. It distinguishes from sibling tools like export_compliance_report, get_compliance_summary, and list_uninsured_subs because it focuses on finding specific documents rather than summarizing or exporting.

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 does not explicitly state when to use this tool versus alternatives. It provides no exclusions or references to sibling tools, and the usage context is only implied by the search verb. No guidance is given on when to choose this over get_compliance_summary or list_uninsured_subs.

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