Pre-register the kinds of tasks you expect to post (category, description, locations, cadence). Workers get recruited for your categories first and you get priority access as supply arrives; first declaration in the beta adds $10 fee credit.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | No | Legwork API key (lw_live_…). Optional if the MCP connection sends an Authorization: Bearer header. Get one with legwork_register. | |
| intents | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the full burden of behavioral disclosure. It mentions the side effect of a $10 fee credit and priority access, but does not explain what happens to declarations over time, whether they are mutable, or any operational limits. It is transparent about the benefit but not about underlying behavior.
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 core purpose, and includes a concrete benefit. There is no unnecessary repetition or fluff; every sentence adds value.
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 nested intents structure and no output schema, the description covers the core concept and benefits but omits details on how declarations are used, how to verify them, or any prerequisites. It is sufficient for basic understanding but not comprehensive for a tool with multiple nested parameters and side effects.
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 50% (only api_key has a description). The description lists the fields within intents (category, description, locations, cadence), which provides some semantics, but it does not elaborate on formats or constraints beyond the schema's enum for category. The description partially compensates for the missing parameter descriptions but not fully.
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 ('Pre-register the kinds of tasks you expect to post') with a specific verb and resource. It distinguishes from sibling tools like legwork_post_task by emphasizing pre-registration for future tasks, and highlights unique benefits (priority access, fee credit).
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 for planning future tasks and notes benefits, but it does not explicitly state when to use this tool over alternatives like legwork_post_task, nor does it provide exclusions or prerequisites. The context is clear but lacks explicit guidance on alternatives.
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 has a distinct purpose: task actions (approve, cancel, post), retrieval (get_task, my_tasks, marketplace), account (register, wallet, topup), messaging (send_message), and intents. No overlapping functionalities.
Mostly verb_noun pattern (cancel_task, get_task, post_task, request_changes, send_message) with some single verbs (approve, register, topup) and nouns (marketplace, wallet) causing slight inconsistency, but all are clear.
12 tools appropriately cover the core operations of a task marketplace without being overwhelming or sparse.
Comprehensive coverage: task lifecycle (create, read, list, update via request_changes, delete via cancel), user management, payments, intents, and marketplace browsing. No major gaps.
