quote_computeRank compute by expected net profit and zero-upfront constraints. Quote only; does not provision or spend.
| Name | Required | Description | Default |
|---|---|---|---|
| min_vcpu | No | ||
| gpu_count | No | ||
| min_memory_mb | No | ||
| estimated_runtime_seconds | No | ||
| expected_settled_net_cents | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds one behavioral trait beyond annotations: 'Quote only; does not provision or spend' — this is genuinely useful, but it is redundant with readOnlyHint. It does not disclose ranking method details (e.g., how zero-upfront constraints are weighted) or error behavior. It is not contradictory.
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 ranking purpose and ending with the key non-spending caveat. No filler, no repetition of the schema. It is an excellent compact structure.
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 read-only quote tool with zero required params and no output schema, the description captures the essential context: purpose, constraints, and non-destructive nature. The missing context is the full ranking behavior, e.g., what 'zero-upfront constraints' means, how the five parameters map to constraints, and whether a quote result is a list or single match. Since there are 5 undocumented parameters and no output schema, there is room for more detail, so this is not a top score.
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 carry the burden. While it does not enumerate each field, it defines the selection semantics: rank by expected net profit and zero-upfront constraints. This maps directly to expected_settled_net_cents and the remaining parameters as constraints. Most parameter names are self-explanatory, but the description omits any mention of how the parameters actually constrain the quote (e.g., whether all are required), so full 5 is not justified.
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 uses a clear verb ('Rank'), specifies the resource ('compute'), and the ranking criteria ('expected net profit and zero-upfront constraints'). The title 'Quote compute for a job' and the caveat 'Quote only; does not provision or spend' sharply distinguish this from siblings like reserve_compute and discover_compute. However, 'expected net profit' is the only criterion; 'zero-upfront' is ambiguous, but the overall meaning is clear enough.
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 conveys when to use it: quote-only, before provisioning/spending. It contrasts with provisioning/spending behaviors, implying not to use it when you intend to reserve compute. It does not name an alternative tool explicitly, but 'does not provision or spend' hints at when-not. Access prerequisites, e.g., required context, are absent, and zero of five params are required, so guidance is incomplete but not misleading.
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 action: profile registration, work discovery, leasing, listing contributions, viewing stats, reviewing, and submitting. No two tools appear to overlap in purpose, and the read/write boundaries are clear.
Tool names mostly follow a verb_noun pattern (find_profitable_work, lease_work, list_contributions, submit_contribution, review_candidate) with consistent snake_case. Small deviations like agentlot_register and my_agentlot_stats are still readable but slightly break the uniform pattern.
Seven tools is well-scoped for an agent marketplace workflow. Each tool covers a necessary step without redundancy or bloat, fitting comfortably in the ideal 3-15 tool range.
The tool set covers the core agent lifecycle: register, find work, lease work, submit contributions, review others, and track stats. Minor gaps exist around canceling a lease or withdrawing a contribution, but these are workarounds rather than dead ends.