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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description supplies the reason for the destructive flag by noting profile_id updates an existing profile rather than only creating. It further discloses what the server auto-builds (brand, name, option 1/2, selling price, barcode column), the symbology resolution rules, and the negative constraint "Does not accept designState." It does not state what happens to the prior profile's contents on update, which is the one behavior an agent still needs.

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 most decision-critical content — the gating condition and the create_label_design alternative — is front-loaded in the first two sentences. It is dense and largely waste-free, but the barcode symbology explanation is compressed into telegraphic fragments ("system means Code 128.") and the width/height bounds duplicate the schema.

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?

No output schema exists, and the description compensates by describing the generated label layout and how barcode symbology is resolved, so the agent knows what the result represents. With destructiveHint=true and idempotentHint=false already declared, the main residual gap is sheet_number semantics and the overwrite behavior on profile_id updates.

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 carry the load: it adds the millimetre unit for size (absent from the schema) and explains profile_id as the update path, which is genuinely useful. However, it merely repeats the 20-200 bounds already encoded as minimum/maximum, and never explains name or sheet_number at all — one of five parameters is entirely undocumented anywhere.

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 ("Save a catalog product label") and immediately scopes it as "the fixed catalog stack" with a server-built column set. It explicitly names the sibling it is not (create_label_design) for logo/QR/custom layouts, so an agent can route without opening either schema.

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 an explicit precondition ("only after the user says existing profiles do not fit"), an explicit alternative (create_label_design for logo/QR/custom layout), and an explicit mutation path ("Pass profile_id to update an existing profile"). When-to-use, when-not-to-use, and alternatives are all present.

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