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

The description discloses important behavioral traits beyond annotations: it may overwrite existing estimates for a specified public recruitment round, and it stops calculation under certain eligibility statuses. The annotations already indicate destructiveHint=true, and the description adds specific context about what gets overwritten and when. It could further clarify the exact nature of the overwrite (e.g., irreversible) but the current disclosure is solid.

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?

The description is a single dense paragraph in Japanese, covering purpose, exclusions, stopping conditions, input constraints, and side effects. It is information-dense but not structured with separators or bullet points. Every sentence earns its place, but the lack of structural breaks makes it harder to parse quickly. Slightly above average due to high information density.

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?

Given the tool's complexity (7 params, destructive side effect, no output schema), the description covers the key decision points: when to stop, what inputs are safe, and how to avoid overwriting. However, it does not describe the output format or methodology version details, and the meaning of several parameters remains implicit. The absence of an output schema increases the burden, but the description still provides enough for an agent to call it correctly in most cases.

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 only 14%, so the description must compensate for undocumented parameters. The description explains the role of target_jgrants_subsidy_id (save to D1 and overwrite) and mentions budget/scope changes as inputs, but it does not explain program_series_key, eligibility_status, program_continuity, target_scope_change, budget_change_percent, or maximum_grant_change_percent in detail. The enum values for eligibility_status are self-explanatory, but the numeric parameters lack context. This is a partial compensation, not full.

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?

The description clearly states the tool's function: it estimates the overall program selection outlook using up to 3 past official selection results from the same program series, using explainable rules. It also explicitly distinguishes itself from individual company selection probability. However, it does not explicitly differentiate from sibling tools like evaluate_subsidy_fit, though the unique focus on program-level outlook and saving to D1 provides some distinction.

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 provides explicit usage conditions: it must stop calculation if eligibility is uncertain/conditional/likely ineligible, and it instructs to only input budget/scope changes when verifiable from official materials. It also gives clear guidance on when to omit target_jgrants_subsidy_id to avoid overwriting existing estimates. This is strong when-to-use and when-not-to-use guidance.

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