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

Beyond the annotations, the description discloses that the tool re-inspects the word through MTW, requires an explicit learner request, preserves text/context/title, uses one operation UUID for idempotent retry, and does not mark the word known, grade recall, or save the whole passage. These are meaningful behavioral constraints and non-effects that help an agent invoke the write operation safely.

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 description is front-loaded with the core save action and the explicit-request condition, then adds only operationally relevant details about ambiguity, preservation, UUID reuse, and excluded effects. It is dense but well structured, and no sentence is redundant.

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 non-read-only, idempotent save tool with seven parameters and limited schema descriptions, the description covers the key usage trigger, prior inspection dependency, ambiguity handling, idempotency, and side-effect boundaries. It is still incomplete on required offset semantics and does not describe success/failure behavior, but the destination check and confirm constant are partly covered by the schema.

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 only 29%, so the description must carry more meaning. It clarifies text as the exact supplied passage, choice as a sense ID selected from offered choices, title preservation, and operation as a reusable UUID. However, it does not explain the offset parameter, which is required and central to selecting one word from the passage, nor does it clarify confirm or destination beyond what the schema provides.

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?

The description states a specific verb and resource: save one word from the exact supplied passage to the connected MTW Backpack. It also distinguishes scope from adjacent actions by saying it re-inspects the word and does not save the entire passage, so an agent can tell this is a targeted save operation rather than a read or inspection.

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?

It gives a clear trigger condition: use only when the learner explicitly asks to save the word. It also gives a special rule for ambiguous meanings, passing only the sense ID the learner selected. It does not explicitly name alternative tools such as inspect_mandarin_word or read_mandarin, so it falls short of full when/when-not/alternatives guidance.

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