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

The readOnlyHint annotation is already set, and the description adds context: it returns at most 30 items and supports comma-separated multiple filters. This source is useful because it clarifies the pagination/limit behavior and the flexibility of filtering, which is not fully evident from the annotation alone. No contradiction detected.

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 compact and front-loaded: the core action and limit appear first, then filtering semantics, then a practical use case. Every sentence adds meaningful guidance without filler, making it easy for an agent to quickly understand when and how to call the tool.

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?

The description is complete enough for a straightforward list tool with no output schema. It covers the main behaviors (latest order, max, filtering) and the intended use case. It does not explain the return structure, but that is not critical given the simple list nature and the derived usage context.

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?

Although the schema already covers 100% of parameters, the description explicitly lists the allowed status values (pending / processing / completed / failed) and endpoint_id values (.ship / oilslick / newbuild / .disappear) which are not defined as enums. This adds practical semantics that an agent can use without opening the schema.

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 action (fetch a list) and the resource (analysis jobs), and adds key constraints: latest order, max 30 items, and filterable by status and endpoint_id. It distinguishes itself from siblings like check_job_status (single-job status) and get_job_result (specific result) by emphasizing the batch listing and the use-case of recovering jobs not tied to a job_id.

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 a concrete usage scenario: "さっきのジョブどうなった？" (what happened to my last job) when the job_id is no longer in the conversation, which is clear guidance for when to use this tool. However, it does not explicitly state when not to use it or mention alternatives beyond the implicit contrast with sibling tools.

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