NumProof

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

With no annotations, the description carries full burden. It lists audit checks but does not disclose whether the tool is read-only, what side effects exist, error behavior, or performance characteristics. The lack of behavioral context is a significant gap.

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, efficiently stating the purpose. No wasted words, though a slightly more structured format (e.g., listing audit types) could improve clarity without losing brevity.

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 simple input schema but lack of output schema and annotations, the description is insufficiently complete. Missing details on return values, error codes, input format constraints, and usage context leave the agent under-informed.

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. It only mentions 'spreadsheet-like rows' but does not define the structure, required fields, or constraints of the 'rows' array. No additional meaning beyond the schema 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 specifies a clear action ('audit') on a resource ('spreadsheet-like rows') and lists specific audit items (footing, balance-sheet ties, margins, provenance). This distinguishes it from siblings like 'diff_rows' or 'verify_claim'.

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 provide any guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites. It only describes what the tool does, leaving the agent to infer usage context.

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. The description does not disclose behavioral details such as idempotency, destructive potential, authentication requirements, return format, or what 'with provenance' means operationally.

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 unnecessary words. It is front-loaded with the core purpose, achieving maximum conciseness.

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?

Despite low complexity (3 params, no output schema), the description is too brief. It lacks details on parameter structure, expected output, and when to use compared to siblings. Important context like what constitutes 'provenance' is missing.

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. The description adds only that 'rows' are 'spreadsheet-like' and that 'rules' and 'rule_pack' are alternatives, but it does not explain their formats, constraints, or how they interact.

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 explicitly states the action 'evaluate' and the resource 'threshold/covenant rules over spreadsheet-like rows with provenance'. It also mentions the two alternative input formats. However, it does not differentiate from sibling tools like audit_rows or verify_claim, which could also involve evaluation.

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 minimal guidance: 'Use either rules or rule_pack.' It does not explain when to use this tool versus alternatives, prerequisites, or when it should not be used.

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 provided, so description carries full burden. It mentions 'provenance' but does not disclose destructive/read-only nature, permissions, rate limits, or any behavioral traits beyond comparing versions.

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 sentence with no wasted words, efficient. However, it could be slightly expanded for clarity without becoming verbose.

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?

Simple tool but description lacks completeness. No output schema, no details on what comparison produces (e.g., diff result). Missing behavioral and result context.

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%, yet description adds minimal meaning ('by numeric row labels'). Parameters 'rows_before' and 'rows_after' are arrays, but no format or type details beyond 'numeric row labels' is implied.

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 compares two report versions using numeric row labels, with provenance mention. It distinguishes from siblings (audit_rows, covenant_rules, verify_claim) by focusing on version comparison.

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 on when to use this tool versus alternatives. The description does not specify context, prerequisites, or scenarios for 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?

Discloses that the tool returns VERIFY/REFUTE/ABSTAIN and provides counterexamples when false. No annotations are present, so the description carries the full burden. However, it lacks details on processing, side effects (likely read-only), or constraints like input format.

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 that efficiently convey the core purpose, outputs, and usage guidance. No unnecessary 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 no output schema, it appropriately describes possible outputs and a counterexample. For a single-parameter tool, it covers the essential context but could specify claim format or error 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?

The sole parameter (claim) is described only as 'a math/finance claim'. With 0% schema description coverage, the description fails to add meaningful syntax, format, or examples beyond the bare 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?

Description clearly states the action (verify), domain (math/finance), possible outputs (VERIFY/REFUTE/ABSTAIN), and use case (before trusting AI-produced numbers). It distinguishes from sibling tools (audit_rows, covenant_rules, diff_rows) by focusing on claim verification.

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?

Explicitly advises using before trusting AI-produced numbers, sums, percentages, or formulas. Does not explicitly list when not to use or alternatives, but the context with sibling tools makes the usage clear.

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