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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false), so the description credits itself by adding non-obvious behavior: the existing coffee's recipes, notes and history are preserved, only purchase facts are new, the active coffee is untouched, and a bag_id is returned from a separate numbering series. It stops short of stating the practical consequence of idempotentHint=false (repeated calls create separate bags), which would be the natural next disclosure.

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 sentences, front-loaded with the core identity of the tool, then inheritance behavior, then the no-side-effect note, then the routing alternative. No filler or repetition of schema content; every sentence earns its place.

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 detailed, yet the description still explains the one surprising part of the return (bag_id belongs to its own series). Together with the routing rule and inheritance semantics, an agent has everything needed to invoke this correctly among the register_*/update_* siblings.

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?

With 62% schema coverage and 13 parameters, the schema already documents required formats and field meanings. The description adds a useful mental model by enumerating which inputs belong to the bag ('roast date, weight, price, state') versus the inherited coffee, and reinforces that bag_notes is about this bag only. It does not clarify the remaining fields like ean, qr_code, storage, or currency.

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 ('register another bag of a coffee that is already in list_beans') and explicitly scopes it to a re-purchase of an existing coffee. It distinguishes itself from the closest sibling, register_coffee, without the agent needing to open either schema, and clarifies that bag numbers are a separate series from bean numbers.

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 both the when ('a coffee that is already in list_beans — the same roaster's product, bought again') and the when-not with the alternative named ('For a coffee that is not in list_beans yet, call register_coffee instead'). It also notes the side effect that it does not change the active coffee, which is a routing-relevant condition.

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