scan_inbox

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

With no annotations, the description carries the full burden and mostly meets it: it discloses the write side effect (creates/overwrites .inbox-plan.yaml), scopes it (no files moved, no vault nodes created), and even spells out the return payload. The phrase "Read-only" sits in mild tension with the fact that it writes and can clobber an existing plan, but the overwrite is called out explicitly in the same block, so an agent is not misled.

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?

Four short lines, front-loaded with the phase and action, followed by side-effect scope, return shape, and ordering. No sentence is filler, and the return-shape line is warranted because no output schema exists.

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?

Complete for a parameterless workflow step: it explains what is scanned, what is written, what is not touched, what comes back (substituting for the absent output schema), and when to call it. The only omission is a pointer to get_inbox_plan() for inspecting an existing plan prior to an overwrite.

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 tool takes zero parameters, so there is no parameter meaning to convey; the baseline for a parameterless tool applies. The description correctly implies no inputs are needed by describing the scan as operating on a fixed directory.

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 (scan loci-stage/), names the workflow phase it belongs to, and says exactly what artifact it produces (.inbox-plan.yaml). The classification step and the plan-file output make it clearly distinguishable from siblings like scan_directory or get_inbox_plan.

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 explicit ordering guidance ("Call this before approve_inbox_plan()") and warns about the overwrite condition, which is exactly the when-to-call context an agent needs. It does not mention get_inbox_plan() as the way to inspect an existing plan before triggering an overwrite, leaving one routing decision to inference.

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