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

The description is consistent with readOnlyHint/destructiveHint=false and adds real behavior beyond the annotations: nothing is written, conflicts are refused when a cell changed since read, the preview_id expires in 15 minutes, and the result carries apply_changes. That is exactly the context an agent needs before chaining into the write tool.

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 no-write guarantee and output shape, then input modes, then the handoff to apply_account_settings; each clause carries distinct information. Even the 繁中 line is a single compact sentence rather than a full duplicate.

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 explains what the result contains (per-cell values, warnings, row errors, apply_changes, preview_id) and its lifetime. Input format, limits, and the downstream call are all covered, leaving no gap for a two-parameter preview tool.

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 100%, so the baseline would be 3, but the description adds meaning: the two input modes (changes list vs. csv) and that the csv mirrors the website download format, plus the base-versus-current conflict rule. The 100-item cap and column rules stay in the schema rather than being reiterated.

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 opens with a specific verb and resource ('Shows what a batch of settings changes would do and writes nothing') and enumerates the returned per-cell old/new values, warnings, and row errors. It is clearly distinguishable from its write sibling apply_account_settings, which it names explicitly.

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?

'Applies before any bulk change, so the user sees the exact cells first' gives a concrete usage rule, and the preview_id handoff to apply_account_settings makes the sequence explicit. It never states when NOT to use it, e.g., a single-account edit that should go through update_account_settings.

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