td_exec

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

With no annotations, the description carries the transparency burden. It discloses that arbitrary Python runs with certain variables in scope and that stdout is returned, but it does not mention possible side effects, persistent state changes, or error 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?

A single front-loaded sentence with zero filler. It communicates the purpose, execution context, and return value efficiently.

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 simple one-parameter tool with an output schema, the description covers the core behavior and return. However, as an arbitrary code execution escape hatch with no annotations, it lacks warnings about destructive capabilities or failure modes, leaving some contextual gaps.

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 has one 'code' string with no description, but the tool description compensates by explaining that the code is Python executed inside TD with specific bindings in scope. This gives the parameter clear semantic meaning beyond its name.

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 a specific action: running Python code inside TD. It also names the execution scope (op, project, ParMode, absTime) and the 'escape hatch' label distinguishes it from the other TD-specific tools.

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 'escape hatch' wording implies it is a fallback for actions not covered by sibling tools, but it does not explicitly say when to use it or when to prefer a dedicated tool. There is no named alternative or exclusion criteria.

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