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

Annotations already cover the read-only, closed-world safety profile, and the description adds real value: what is returned (per-form filled-field counts), that multiple cases are distinguished by creation timestamp/case_id, and that nothing is deleted. It does not mention result limits or ordering, which is a minor gap given an output schema exists.

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 purpose and use case, then alternatives, with no filler. However, the new_draft=true sentence is somewhat tangential for a zero-parameter list tool and takes up space that could confuse which tool the flag applies to.

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?

Adequate for a simple zero-param read tool: what is returned, how cases are identified, and how to proceed afterward are all covered, and return shape is handled by the output schema. The only soft spot is the ambiguous new_draft reference, which is not this tool's parameter.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The mention of new_draft=true actually belongs to a sibling tool, not this one, but it is framed as routing context.

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 with scope: returns in-progress applications plus per-form filled-field counts, and names the use case (resuming). This clearly separates it from siblings like start_application or delete_application, which mutate rather than list.

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?

Explicitly routes to alternatives: resume via start_application(subsidy_id, case_id), create a parallel draft with new_draft=true, delete a single case with delete_application. The when-to-use condition ('前回の続きから再開するときに使う') is stated up front.

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