gdb_start_session

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

With no annotations provided, the description fully carries the burden. It discloses that warnings are reported in a 'warnings' field, that a session_id is returned and must be used with other tools, and explains the required sequence for core dump symbol resolution (sysroot after core load). This is comprehensive behavioral disclosure.

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 somewhat lengthy and mixes parameter listing with usage notes. It could be more structured, perhaps by separating parameter details from procedural notes. While every sentence adds value, the overall flow could be tighter. There is some redundancy with the schema descriptions.

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 the tool (7 parameters, no output schema, important behavioral nuances), the description covers all necessary aspects: what the tool does, how to use parameters, key warnings, the returned session_id, and critical ordering for core dump debugging. It is complete and effectively supports an AI agent in correct invocation.

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 coverage is 100%, but the description adds significant value beyond the schema. For example, it explains the --core flag for core dumps and the important ordering for symbol resolution, provides examples for init_commands and working_dir, and clarifies the use of env. This extra context is highly beneficial for correct usage.

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 it starts a new GDB debugging session and lists the actions it can perform (load executable, core dump, init commands). It differentiates from sibling tools (e.g., gdb_set_breakpoint, gdb_continue) by focusing on session initialization. The purpose is specific and unambiguous.

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 clear guidance on when to use the tool (starting a session) and gives important usage notes, especially for core dump debugging with sysroot. It does not explicitly state when not to use or list alternatives, but the context of sibling tools and the session-oriented nature mitigates this. The warnings about critical issues in the response add value.

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