Kz Save

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

With no annotations, the description carries the full burden and does well: it discloses the network side effect of the default path, that out_path mode performs no upload at all, the allowlist gate that can block the call, and the extra side effect of archiving the uploaded file under backups/. It does not mention overwrite semantics for an existing .kzp, error behavior, or authentication expectations.

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?

Three short lines, front-loaded with the core action, then each mode on its own line, then the archival side note. The parenthetical and stacked clauses in line three are dense but every sentence carries information. Written in French while the tool names and siblings are English, a minor consistency friction.

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?

An output schema exists, so return values need not be explained, and the description covers both execution paths plus the allowlist constraint. The remaining gap is that plan_id is referenced as a gating value but appears nowhere in the input schema, leaving the agent to infer it comes from prior session state.

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 0%, so the description must compensate, and it does for both parameters: it explains the default title resolution (server-side plan title) and, most importantly, that out_path switches the tool into a local-write-only mode rather than merely naming a destination. It stops short of describing the expected path format or whether directories are created.

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 concrete verb and resource ('Enregistre le plan') and immediately splits the operation into two distinct modes (local .kzp write vs. API POST). It does not explicitly contrast itself with siblings such as kz_open or kz_get, but the save semantics are unambiguous on their own.

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 mode selection: supply out_path for a purely local export with no upload, otherwise it POSTs to the API. It also states a hard precondition (plan_id must be in KZ_ALLOWED_PLANS). No named alternative tool is offered for someone who wants copy/duplicate behavior (kz_copy_plan), which keeps it below 5.

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