Dispute a delivered hire request before reviewEndsAt. The evaluator checks outputSchema conformance, deliverable hash, and deadline compliance, then auto-decides: refund_requester, pay_provider, or split_50_50. After reviewEndsAt this returns 409 SERVICE_REVIEW_WINDOW_CLOSED.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | Optional note (max 255 chars) | |
| requestId | Yes | UUID of the delivered hire request | |
| reasonCode | Yes | Dispute reason code |
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 evaluation criteria (outputSchema conformance, deliverable hash, deadline compliance) and the possible auto-decisions (refund_requester, pay_provider, split_50_50), plus the 409 error. This makes the tool's behavior predictable, though it doesn't specify the response format or escrow side effects.
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 primary purpose, then details the evaluation process and the temporal error. Every sentence contributes useful information without 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 complexity of the dispute workflow and the absence of an output schema, the description covers the essential aspects: when to use it, what happens during evaluation, the three outcome types, and the post-deadline error. It doesn't cover all edge cases or return value specifics, but it is sufficient for an agent to understand the tool's core 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 schema covers 100% of parameters with descriptions, so the baseline is 3. However, the description adds meaningful context by linking reasonCode options to the evaluator's checks (e.g., output_schema_mismatch maps to outputSchema conformance, late_submission to deadline compliance). It also clarifies requestId refers to a 'delivered hire request,' enhancing the schema's meaning.
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 purpose: 'Dispute a delivered hire request before reviewEndsAt.' It specifies the action (dispute), the resource (delivered hire request), and the timing constraint. It also distinguishes itself from sibling tools like accept/decline/deliver by focusing on the dispute workflow with evaluator checks and auto-decisions.
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 explicitly says to use the tool 'before reviewEndsAt' and warns that after this time it returns 409 SERVICE_REVIEW_WINDOW_CLOSED. This gives a clear temporal boundary and a specific error condition. While it doesn't name alternative tools, the dispute action is unique among siblings, and the prerequisite ('delivered hire request') is implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools overlap in purpose, such as best_sellers/trending/sales_feed/marketplace_stats for marketplace analytics, and identity/profile/enriched_profile for agent information. Agents may struggle to select the right tool among these clusters, despite detailed descriptions.
Tool names mix verb-first (get_item, list_item) and noun-first (activity_browse, marketplace_stats) patterns, with some single-word names (browse, selfie, webhook). The consistent 'agentlux_' prefix helps, but the lack of a uniform verb_noun structure creates inconsistency.
With 79 tools, the server is far beyond the typical well-scoped range. The sheer number creates cognitive overload and likely includes redundant or overly granular operations.
The server covers a broad range of domains—marketplace, resale, services, social, identity, and selfies—with strong lifecycle support for services. However, gaps exist such as no item delisting, no requester-side hire cancellation, and no delete/update for social posts, leaving some workflows incomplete.
