export_kit

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

Annotations cover the safety profile (readOnly/idempotent/non-destructive), and the description adds substantial context beyond them: the gating preconditions, the refusal behavior, and the exact shape of the result (embedded application/zip resource, kit:// URI, on-disk path). The 'fails unless user_approved' gate is exactly the kind of behavioral disclosure the schema cannot carry.

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?

Front-loaded with the core action, and no sentence is filler, but the heavy nested parentheticals ('(the user has seen and agreed)', '(an embedded resource, application/zip, also readable later as kit://<file name>)') make it dense and slow to parse. Information is earned, but the packaging is run-on.

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 gated export tool with no output schema, the description covers preconditions, refusal behavior, and the returned artifact and its location, which is most of what an agent needs. Minor gaps remain: error/response shape on refusal and what 'the two finished sheets' refers to.

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 description coverage is 0%, so the description must compensate. It defines user_approved's meaning ('the user has seen and agreed') and path's behavior ('local servers; default its work folder'), and the kit argument is implicitly the kit being exported. This meaningfully exceeds the bare anyOf/boolean 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?

States a specific verb and resource ('Write the kit file (.kit.zip)') and enumerates the archive contents (kit.json, sheets, pictures, previews). This clearly separates it from siblings like import_kit (inverse), preview_kit (no artifact), and render_sheets (produces sheets, not the bundle).

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?

Explicitly conditions invocation on 'the compare loop shows the kit matching the user's pictures' and routes the agent to get_kit_spec's workflow. It further states the refusal conditions (never compared, invented parts, missing user_approved), giving both when-to-use and when-it-will-fail.

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