run_command

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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description is consistent with that. It goes well beyond annotations by disclosing the exact returned fields, the constraint that BPP must be launched from `directory` because data paths are relative, that long runs take hours or days, and which fields are null when unset.

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?

Front-loads the core behavior and the 'does NOT run BPP' caveat in the first two sentences, then uses a compact field list. The length is justified because there is no output schema, though the return-value breakdown is slightly verbose.

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?

With no output schema and a single undocumented parameter, the description fully carries the load: it enumerates every returned field (directory, command, shell, jobname, threads, notes) and their meaning, and points to lookup_docs/set_keyword for follow-up work on threads.

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 single parameter `ctl` has no schema description (0% coverage), so the description must compensate. It refers generically to 'the control file's folder' and 'the file's current values', which implies `ctl` is the control file path but never states it outright or its format.

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?

States a specific verb and resource: it produces the command the user runs to start the full analysis, and explicitly says it does NOT run BPP. This cleanly separates it from execution-oriented siblings like smoke_test and from file-authoring tools like make_control_file.

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?

Gives an explicit ordering rule ('Call last, once lint_control_file reports server.status "valid" and smoke_test did not fail') plus a clear exclusion: this server never starts the real run. The agent knows both the precondition and the boundary of the tool.

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