execute

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It thoroughly explains return statuses (completed, pending, error), what 'pending' means, and how to handle it. It also alerts the user to dangerous or slow commands (e.g., !analyze -v), blocked commands, and the fact that commands are forwarded to cdb.exe. This goes well beyond a basic description.

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?

Although the description is long, it is efficiently structured with clear sections for return values, pending behavior, and common commands. Every sentence adds practical value—examples, cautionary notes, or status handling—so the length is justified and the content is front-loaded with the core purpose.

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 complexity of a CDB command execution tool, the description is remarkably complete. It covers return formats, asynchronous behavior, common command usage, safety exclusions, and provides pointers to sibling tools for each scenario. The output schema is embedded in the description, and the parameter guidance is sufficient for an agent to operate correctly.

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 input schema has 0% description coverage, so the description must compensate. It explains that 'command' is a CDB string and hints at the timeout parameter (e.g., 'use large timeout' for !analyze -v), but it does not explicitly document the 'timeout' or 'session_id' parameters or their expected formats. This partial compensation earns a mid-range score.

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 opens with a clear, specific verb and resource: 'Send a CDB command to the current debug session.' It further identifies this as 'the core tool for interacting with CDB,' explicitly distinguishing it from sibling tools like get_output, interrupt, and close_session, which handle related but distinct operations.

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 provides explicit guidance on when to use this tool versus alternatives: it notes that pending commands should be followed by get_output, interrupt, or wait_for_prompt, and that q/qq/qd are blocked, directing the agent to 'use close_session instead.' This makes when-to-use and when-not-to-use behavior clear.

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