plan_from_factory

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

Annotations declare a non-readonly, non-destructive, non-idempotent write, and the description adds real substance on top: recipes get pinned, inputs supplied, surplus exported under the stated flow stance, equal plans are reused, and differences are recorded in notes. The gaps are the cryptic "sunk under the flow stance" clause and no statement of permissions or what a failure looks like.

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 core purpose is front-loaded in the first sentence and total length is short. But the second paragraph is dense jargon with an opaque parenthetical, so it is compact at the cost of parseability rather than genuinely efficient.

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 a 5-parameter mutation with no output schema, the description covers the semantics of the write reasonably (pinning, reuse, export, notes) but leaves the return unknown and half the parameters unexplained. It is enough to avoid a wrong call, not enough to call it confidently with the right argument values.

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 60%, and the description compensates for none of it: save, as_of, world, and factory are never explained (as_of's sav: token hint lives only in the schema). Worse, "Differences from the build go in the notes" references a "notes" concept that is not a parameter at all, which can send an agent looking for a field that does not exist.

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?

"Save a plan mirroring a named factory as built, to edit or extend" specifies a concrete verb (save/mirror) and resource (a factory-derived plan) plus the intended follow-on use. It is clearly understandable without opening the schema, but it never differentiates itself from plausible siblings such as plan_factory, import_plan, or edit_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?

Phrases like "as built, to edit or extend" imply the situation (you want an editable copy of an existing factory rather than a fresh solve). However, there is no explicit when-to-use/when-not and no named alternative, even though siblings plan_factory, import_plan, and commission_plan occupy adjacent territory.

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