Analyze an optimization problem for free — returns a machine-readable decision block: recommended mode/backend, estimated runtime, USDC price, benchmark evidence. Always call this before paying for cortex_optimize.
| Name | Required | Description | Default |
|---|---|---|---|
| problem | Yes | Optimization problem to analyze |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It discloses cost ('for free'), output contents, and workflow prerequisite. However, it does not explicitly state that it is read-only or has no side effects, leaving some ambiguity about whether it executes any optimization or stores data.
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 action and output, and includes a clear workflow instruction. Every phrase earns its place, with no unnecessary words.
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 absence of an output schema, the description compensates by listing the return fields (mode/backend, runtime, USDC price, benchmark evidence). It also provides cost and usage context, making it sufficiently complete for an agent to decide when to invoke the tool.
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 description coverage is 100%, with detailed descriptions of problem, n, data, linear, and quadratic fields. The tool description adds no additional parameter semantics beyond referring to an 'optimization problem', so baseline 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?
The description clearly states the tool 'Analyze an optimization problem for free' and lists specific outputs (recommended mode/backend, estimated runtime, USDC price, benchmark evidence). It explicitly distinguishes from the sibling cortex_optimize by saying 'Always call this before paying for cortex_optimize'.
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?
Provides explicit usage guidance: 'Always call this before paying for cortex_optimize' establishes a clear workflow and names the alternative. The description implies this tool is for free estimation, while cortex_optimize is the paid execution step.
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 operation: chat, HTTP automation, JSON transform, optimization planning/execution/polling, backend listing, research search, token price, and wallet balances. Related optimization tools are clearly separated into estimate, solve, and poll stages, so an agent can select the right one without ambiguity.
All tools share a snake_case 'cortex_' prefix, but the suffix pattern is inconsistent: some are verb_noun (get_job, list_backends), some are single verbs (optimize), and some are noun phrases (token_price, wallet_balances, ai_chat). The names are readable but do not follow a uniform convention.
Ten tools is a well-scoped size for a multi-purpose cloud API covering AI, automation, optimization, research, and crypto queries. Each tool maps to a distinct paid or free endpoint, and there is no obvious bloat or redundant functionality.
The optimization workflow is well covered with estimate, backend listing, solve, and job polling. Minor gaps exist, such as no job cancellation and read-only wallet tools with no transfer capability, but the main workflows agents would attempt can be completed without dead ends.