build_run

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

No annotations are supplied, so the description carries the full safety burden and does it well: it discloses shell:false execution, workspace-bound cwd, a timeout, rejection of shell metacharacters, an environment gate, and an explicit confirm flag. It does not say what happens on failure or whether output is captured, keeping it short of a 5.

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?

Two dense sentences with the safety constraints front-loaded and zero filler; every clause carries a distinct constraint an agent must respect before calling.

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 an execution tool with no annotations and no output schema, safety and eligibility are covered thoroughly. The gap is result behavior: with no output schema present, the description should say what a run returns (stdout/stderr, exit code, timeout behavior) so the agent knows how to consume the call.

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 80% and the enum plus descriptions already document command, args, cwd, and confirm, so the baseline is 3. The description reinforces the invariants (allowlisted tool, cwd constrained to workspace, restricted argument characters) but adds no syntax or default details beyond the schema.

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?

Specific verb+resource: 'Run one allowlisted build command' plus the isolation model (shell:false, workspace-bound cwd). It does not explicitly contrast itself with sibling build tools like build_analyze or build_ps2, so the agent must infer that this is the raw execution tool.

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?

Given eligibility conditions (RETRACE_ALLOW_WRITE=1, confirm=true) and an implied one-command-per-call scope, which is useful when-to-use guidance. However, it never states when to prefer this over build_analyze or build_ps2, nor when not to use it, so alternative selection is left to inference.

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