Guard Next Action

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

With no annotations, the description carries the full burden. The 'without modifying project files' clause is a useful safety signal, but nothing is said about whether it reads or writes guard state, how the 'bounded' constraint is enforced, or what form the returned action takes.

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?

One sentence, front-loaded with the verb and result. Nothing is padded, though the terseness crosses into underspecification rather than efficiency.

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?

There is no output schema, so the description should explain what a 'bounded action' contains and how the agent should consume it. The nature of the return value is left entirely undefined, which is a real gap for a tool whose whole purpose is producing a next-step payload.

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?

Single optional `root` parameter is fully described in the schema (100% coverage), so the schema already does the work. The description adds nothing about path semantics or defaults, which is the expected baseline for full coverage.

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?

Names a specific verb ('Return') and object ('next bounded action for an AI coding-agent loop'), and adds a non-mutation qualifier. However, 'bounded action' is unexplained jargon, and it doesn't distinguish itself from siblings like codapult_guard_propose or codapult_guard_check, which plausibly also return guidance.

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?

No indication of when this tool should be chosen over codapult_guard_propose, codapult_guard_check, codapult_guard_verify, or the other nine siblings. The agent must guess at the loop-step position this tool occupies.

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