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

Annotations already declare readOnlyHint and openWorldHint, yet the description adds substantial behavioral context beyond them: xlsm macros are preserved but never executed, pagination must reuse the same retrieval conditions via next_cursor/next_offset, max_bytes is a UTF-8 JSON budget with format-dependent defaults, and how_to/profile_candidates appear only on the first call. This is exactly the extra context the annotations do not cover.

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-loads purpose in the first fragment and organizes the rest by format, exclusivity, pagination, and budget, so it is easy to scan. It is dense and telegraphic, and the max_bytes/MCP-wrapper caveats add length that only marginally serves tool selection.

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 12-parameter, multi-format tool whose output schema already documents return values, the description still covers format behavior, exclusivity, pagination chaining, and empty-vs-mandatory semantics — enough to call it correctly. The only noticeable gap is the unexplained limit/include_formulas parameters.

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 0%, so the description carries the full burden, and it explains most parameters well (page is 1-based, table is 0-based, targets take 'sheet!address' IDs, only_empty means unfilled candidates not mandatory-field detection, max_bytes range 4096–262144). It leaves limit and include_formulas unexplained, so it compensates but not completely.

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?

Opens with a specific verb+resource ('欄の一覧' — list the fields of a form) and then distinguishes itself from the sibling view_form ('欄は空いた場所の候補で、view_form で画像を確かめる'). An agent can tell it reads field structure rather than filling or validating without opening the schema.

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 explicit mode-selection rules per format (Excel=outline/sheet/sheets, PDF=per-page vs page, Word/RTF=body and table, PowerPoint=targets), states the exclusivity constraint (sheet・sheets・targets・table は排他), and routes to view_form for image confirmation. When-to-use and when-to-use-an-alternative are both covered.

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