freee application detail

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable behavioral context beyond these: it specifies the exact data returned (applicant, dates, content, etc.), and for 勤務時間修正 it discloses the structured workTimeChange.before/after fields, including the semantics of null time fields (freee displayed 未入力). This enriches the agent's understanding of tool output and edge cases.

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 concise: two sentences. The first sentence front-loads the core purpose and output summary. The second sentence adds a specific sub-type behavior in a tight, information-dense manner without fluff. Every word contributes value.

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 tool with a single parameter and no output schema, the description adequately covers the return content (applicant, dates, content, reason, comments, approval route, automatic checks) and special case (勤務時間修正). It also explains the null semantics, which is essential for interpreting results. There is no missing critical behavior for the intended use.

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 100%: the only parameter 'id' has a description ('The numeric No. shown in the freee application list'). The tool description does not add any parameter details beyond the schema. Since the schema already fully documents the parameter, the baseline of 3 is appropriate.

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 'Read one application' with a specific verb and resource, and enumerates the returned components (applicant, dates, content, reason, comments, approval route, automatic checks). This differentiates it from sibling list/detail tools like freee_approvals_list and freee_personal_application_detail. The mention of a supported 勤務時間修正 subtype further specifies scope.

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 implies usage: when you need to read a single application by id. It states 'Read one application', which gives clear context. However, it does not explicitly mention when not to use it or point to alternatives (e.g., 'for listing, use freee_approvals_list'). Despite lacking explicit exclusions, the context is unambiguous.

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