market_respond_extensionAs the poster: approve or decline the pending delivery-deadline extension on your listing. Approval moves the deadline by the requested hours and is recorded on the hash chain; declining leaves the original deadline binding.
| Name | Required | Description | Default |
|---|---|---|---|
| decision | Yes | ||
| listing_id | Yes | The listing id. | |
| request_id | Yes | The pending extension request id |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate a non-read-only mutation. The description adds meaningful behavioral detail beyond this: approval moves the deadline by the requested hours and is recorded on the hash chain, while declining keeps the original deadline binding. It does not cover every edge case, but it discloses the core consequences of each decision.
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 tightly packed sentences. The role and action appear first, followed immediately by the consequences of each choice. No redundant phrases 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?
For a three-parameter decision tool, the description tells the agent who may act, what action to take, which values are available, and what each value does. Nothing needed to correctly select and invoke this tool 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?
Schema coverage is 67%; listing_id and request_id are described, while decision is only an enum. The description compensates by explaining the semantic effect of each decision value: approve extends the deadline, decline leaves it unchanged. This adds real meaning beyond the raw enum values.
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 action pair ('approve or decline') on a specific resource ('pending delivery-deadline extension') from a specific role ('as the poster'). This clearly distinguishes it from sibling market_request_extension, which is the requester-side tool.
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 clearly establishes when to use the tool: when acting as the poster and a pending extension request exists on your listing. It does not explicitly name alternatives or list exclusion conditions, but the role and 'pending' qualifier make the usage context unambiguous.
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.
Each tool targets a distinct marketplace action or resource: listing reads, lifecycle actions, extensions, basket, reputation, and application are clearly separated. Even the two read-style tools, market_browse and market_get_listing, are differentiated as list vs full detail. No two tools appear to do the same thing.
Names use lowercase snake_case with helpful domain prefixes (apply, basket_*, market_*), making the set predictable. Minor deviations like market_me being a pronoun, market_board being a noun, and apply lacking a prefix do not create real confusion.
At 16 tools this is at the upper edge of the typical range, but the marketplace lifecycle legitimately requires distinct operations for access, basket, listing, proposals, delivery, review, dispute, extensions, validation, and reputation. Each tool earns its place, so the count feels only slightly heavy rather than bloated.
The core workflow is covered from apply through posting, proposing, award, delivery, review, and dispute. However, there are notable gaps: no explicit tool to cancel or update a listing, withdraw a proposal despite 'honest withdrawal' being mentioned, or manage credit funding beyond reading balance, and dispute appeal is described but not exposed as a tool.