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

Annotations already cover readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable behavior beyond those: officialRate may be null, the agent must not infer a rate from missing data, and user-facing labels must emphasize 'past official selection rate' rather than individual probability. This is meaningful context that prevents misuse.

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 main purpose is front-loaded in the first sentence, and the two following sentences each add an essential constraint about handling null rates and user-facing terminology. There is no fluff or repetition, and the structure is easy for an agent to parse.

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 read-only lookup with one parameter, the description covers the returned content (counts, selection count, official rate, supporting basis), the possibility of officialRate being null, and presentation rules. It does not specify the exact response shape or behavior when no record exists, but it is complete enough for correct invocation and basic interpretation.

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%, but the single parameter jgrants_subsidy_id is directly explained in the description as 'Jグランツ補助金ID', making its meaning clear. The description also clarifies that the data is stored and keyed by that ID. Format details are minimal, but with one required self-descriptive parameter this is sufficient.

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 states a specific verb ('返します') and a precise resource ('公募回別の公式申請件数・採択件数・公式採択率と根拠') scoped to a JGRANTS subsidy ID. Its read/statistics semantics clearly distinguish it from siblings like record_official_selection_statistics and estimate_program_selection_outlook without needing to name them.

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 gives clear behavioral constraints for presenting results ('officialRateがnullの場合は割合を推測しない', '個別企業の採択確率とは説明しない'), which guides correct use. However, it never explicitly states when to prefer this tool over alternatives such as estimate_program_selection_outlook, so tool-selection guidance is only implied.

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