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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower; the description still adds the useful edge case that a null card means no applicable Mandarin target. It also restates card contents (pinyin, meaning status, parts, alternatives) that the output schema likely already documents, which caps the credit slightly.

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 action and target, then constraints, then return semantics, then the negative boundary. Dense and largely waste-free, though the enumeration of card fields partially duplicates the output 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?

For a small read-only lookup with full annotations and an output schema, the description supplies everything an agent needs: offset counting rules, passage-preservation requirement, and null-result meaning. Only the optional title parameter is left unaddressed, which is minor.

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?

At 67% schema coverage the description meaningfully adds to the offset parameter by warning to count Unicode code points rather than UTF-16 units, the classic source of off-by-N bugs. It reinforces the 'exact passage' constraint on text but says nothing about the optional title parameter, which neither schema nor description explains.

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 ('Inspect the Mandarin word or pattern at a Unicode code-point offset in the exact supplied passage') and names the return artifact, MTW's contextual word card. The closing clause 'Does not save or grade learning' implicitly separates it from save_mandarin_word.

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 real calling conditions (preserve the original passage, count code points, null means no applicable target), but never says when to choose this over sibling read_mandarin. The agent must infer the split between inspection-with-context and plain reading.

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