BanProof AI

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

With no annotations, the description carries the full burden and does well: it discloses the detection categories, the return payload (flagged phrases, reasons, safe rewrites, overall risk level), and that a product URL triggers cross-checking of overclaims. It does not explicitly state that the operation is read-only and non-persistent, nor anything about latency or script length limits, which keeps it short of a 5.

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, front-loaded with the core verb and resource, followed by a compact violation taxonomy and the return shape. The eight-item detection list is long but each entry is a distinct, actionable category, so it earns its space; a slightly tighter grouping would push it higher.

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?

No output schema exists, and the description compensates by naming the return fields and the risk-level summary. For a two-parameter, single-shot analysis tool this covers what an agent needs to call it correctly; only edge details (input size limits, whether results are persisted) are absent.

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 100% and both parameters are documented in-schema, including the conditional behavior of product_url. The description adds no parameter-level detail beyond what the schema already provides, so the baseline 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?

States a specific verb (audit) and resource (affiliate video script) with named platforms (TikTok Shop, Amazon) and an enumerated set of violation classes. This is clearly distinct from the only sibling, generate_appeal, which is a downstream remediation action rather than a check.

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 context of use is strongly implied — you audit a script to catch policy violations before publishing — and the enumerated detection categories hint at when it is relevant. However, there is no explicit 'use this when' statement, no mention of prerequisites or ordering relative to generate_appeal, and no stated exclusions (e.g., non-affiliate content).

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 behavioral burden. It does disclose useful traits — the output is 'ready-to-submit' and is constrained to TikTok's 800-character appeal limit — which tells the agent the result is submission-ready rather than a draft outline. However, it does not say what form the response takes (plain text vs. structured fields), whether it also returns rationale or character counts for Amazon/YouTube, or whether generation is deterministic.

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, front-loaded with the purpose before the input instructions, with no filler. The final sentence slightly duplicates what the schema already declares for the two required parameters, which is the only wasted motion.

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 two-parameter generation tool with no output schema and no annotations, the description covers the core contract but leaves the return shape underspecified beyond 'ready-to-submit'. It also gives no platform-specific caveats other than TikTok's character cap, leaving an agent unsure what the Amazon or YouTube outputs guarantee.

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 100% and both parameters are fully documented in the schema, including the platform enum. The description only restates the mechanics ('paste the violation notice text', 'specify the platform') without adding constraints such as minimum notice length or what happens with truncated notices. Baseline 3 applies when the schema does the heavy lifting.

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 — 'Generate a ready-to-submit appeal response' — and scopes it to three named platforms (TikTok, Amazon, YouTube) for policy violation notices. This is clearly distinct from the only sibling, audit_script, so an agent can route without opening the schema.

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?

It gives a concrete usage cue: use this when you have received a violation notice, paste that notice text, and specify the platform. That establishes the trigger condition well. It stops short of explicit exclusions or naming alternatives for cases like auditing an existing script (audit_script), so it is strong but not fully prescriptive.

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