mathematica_verify

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It does disclose one useful trait — execution happens in a clean kernel, implying no state leakage — but says nothing about what gets written to out_path, how failures are reported, timeout behavior, or what happens with previous_path.

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?

One short sentence with no wasted words, and the key idea (clean-kernel re-execution plus comparison) is front-loaded. But the brevity reads as under-specification rather than efficiency for a five-parameter tool.

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 verification tool with three required paths, an optional previous result, a timeout, no annotations, and no output schema, a single sentence is far too thin. The agent knows the gist but lacks enough to call it correctly the first time.

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% across five parameters, so the description must compensate and does not. It never distinguishes task_path from code_path, never explains what previous_path is for, and never mentions the timeout default.

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 names a specific verb+resource: re-execute checks in a clean kernel and compare against reference results. That is a recognizable verification operation distinct from running or computing. It does not, however, explicitly contrast itself with siblings like mathematica_run or mathematica_compute, so an agent must infer the difference from 'clean kernel'.

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?

There is no statement of when to use this tool versus mathematica_run, mathematica_compute, or mathematica_lint. The phrase 'in a clean kernel' hints at isolated verification but never spells out the condition that should select this tool over re-running code.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.