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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the overwrite nature is partly covered; the description reinforces it with '（置き換え）' and adds real context beyond annotations – clear semantics, from_profile batch behavior, and the meaning of rejected (not saved) vs warnings (saved). It stops short of describing return structure or permission requirements.

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 the core save/overwrite semantics before the conditional details, and nearly every line carries distinct information. The telegraphic fragment style is dense but efficient; minor readability cost, no filler sentences.

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?

An output schema exists, so return-value detail is not required, and the description still explains the response concepts rejected/warnings/progress enough to act on them. Combined with the per-format key guidance and the sibling pointer, an agent has what it needs to call this correctly for a 5-param mutation 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 0%, so the description carries the burden, and it does: it explains values as field-ID→string, clear as cancellation, sheet as the Excel sheet selector, and from_profile's batch behavior. form_id is left implicit but is obvious from the name; nested-object key syntax for Excel/PDF is spelled out, which is above baseline.

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+resource: save field-ID→string pairs into a form, with overwrite semantics ('保存（置き換え）'). It explicitly routes the multi-form case to the sibling fill_forms, so an agent can distinguish it from that tool without opening either 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 conditional usage: from_profile=true fills all blank profile-candidate fields at once, and '複数様式は fill_forms を使う' names the alternative for multiple forms. It also clarifies the field-ID format per document type (Excel sheet/address, PDF p1.f12), removing ambiguity about when each form applies.

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