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

Beyond the destructiveHint=true annotation, the description discloses concrete destructive behavior: notes are overwritten wholesale, an empty string erases the note, 300-char overflow is truncated and flagged with truncated: true, and moving favorite→watching silently deletes shares and acquisitionPrice. It also documents the watching-count upper limit blocking a move and the partial-update guarantee (registration/last-check dates unchanged).

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 operation is front-loaded in sentence one and the body is organized by concern (categories, moveTo, shares, note, limits, errors). It is long but nearly every sentence carries a distinct rule; minor tightening of the category explanations would be possible.

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?

With no output schema, the description still communicates the return signals an agent needs (notFound: true, truncated: true) and covers all six parameters plus the cross-category edge cases. Nothing essential for correct invocation is missing for a mutation tool of this complexity.

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?

Even with 100% schema coverage, the description adds meaning the schema cannot: shares/acquisitionPrice are only valid on favorite and null clears them, note is only valid on watching and empty string clears it, and category omission has conditional fallback/error semantics. These are genuine semantic rules, not restatements of the field descriptions.

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 first sentence names a specific verb (書き換えます) and the exact resources it touches (note, shares, acquisitionPrice, category) on an already-registered watchlist stock. It is immediately distinguishable from siblings add_to_watchlist (which registers), get_watchlist (which reads) and remove_from_watchlist.

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 explicitly routes the agent: unregistered codes return notFound and the description names add_to_watchlist instead; to append a note it tells the agent to read via get_watchlist first and pass the full text. It also states when to use moveTo versus category, and what happens when category is omitted (single match rewritten, ambiguous match errors out).

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