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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true. Beyond that, the description adds genuine behavioral context: case_id=null signals a missing template or fetch failure, the same request should not be repeated, and failure paths route to original_url. It still doesn't describe the side effect of 'starting' a case (draft creation, state change).

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?

Purpose is front-loaded in the first clause, and the remaining sentences each carry a distinct rule (writable routing, null case, retry guidance, preparation, original_url fallback). Dense but no filler.

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 workflow-start tool with an output schema, the description appropriately focuses on interpreting results (case_id, reason, next_steps, forms.writable, preparation) rather than re-documenting the return shape. The only gap is the tool's own mutation semantics, which no field covers.

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% for the single required parameter, so the description must compensate. It identifies subsidy_id as the 制度ID (subsidy/program identifier) being acted on, but adds no format, lookup source, or validation detail beyond that.

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 ('制度IDから案件を開始・再開する' – start/resume a case from a subsidy ID), which is clear and distinct from siblings like get_subsidy or list_applications. It does not, however, explicitly contrast itself with those siblings, so it stops short of a 5.

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?

The description is rich in downstream routing (writable=true → inspect_form→fill_form; writable=false → original_url; import_official_form when the user asks), which implies the workflow context. But it never states the condition for invoking start_application itself versus alternatives, so usage is implied rather than explicit.

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