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

Annotations already declare readOnlyHint=true/openWorldHint=false, so safety is covered, but the description adds real behavioral context: the four possible status values (fail/warning/unknown/pass), what IS checked (input rules, formula references), and explicitly what is NOT verified (required fields, supplementary amount calculations). This scope-boundary disclosure is valuable and goes beyond the annotations; it only lacks any note on cost/pagination behavior.

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 nature of the operation ('読み取り検査'), then scope, then routing. Every sentence carries information (status values, check coverage, alternatives) with no filler. Dense but not wasteful.

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 format need not be re-explained, and the description covers the remaining essentials: status semantics, validation coverage limits, and how to inspect findings or combine with export. Adequate for the tool's complexity, with only minor room for detail on case_id or unsaved/missing-field outcomes.

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?

Top-level schema description coverage is 0%, so the description must carry the load for `expected` – which it does, explaining that the caller passes what was entered and that the server matches it against field headers and stored values, and that monetary amounts must always be supplied. `case_id` is left unexplained but is self-evident from the required-parameter name.

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 ('読み取り検査' read-only inspection that validates entered content), plus the mechanism (`expected` compares original values/row-column headers against saved values). It differentiates itself from both inspect_form (findings) and validate_and_export_application (combined validate+output), so an agent can pick it 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?

Names two alternatives with the conditions that select them: use inspect_form(targets=[欄ID]) to see flagged fields, and validate_and_export_application when inspection and output should be combined. It also gives a hard usage rule ('amounts in tables must always be passed'), leaving nothing to inference.

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