save_bookmark

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it discloses the critical trait: this is an external write to Pinboard gated by mandatory user confirmation. It also clarifies that the summary is a distinct Pinboard-oriented artifact, not the user-facing explanation. It omits minor behaviors like duplicate-URL handling, auth needs, and failure modes, but the essential side-effect safety information is present.

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 long, but every sentence earns its place: the purpose is front-loaded, and the critical preconditions are flagged with 【重要】. The structure separates the mandatory workflow from parameter guidance, making the density scannable rather than bloated.

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 4-param tool with no output schema and no annotations, the description supplies the essential operational context: the prerequisite explanation, the confirmation gate, and the summary/tags constraints. Missing items (duplicate bookmark behavior, return value, error cases) are minor and do not impair correct invocation.

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% so the baseline is 3, but the description adds real value beyond the schema. It specifies that summary must be a condensed Pinboard-saving text separate from what was presented to the user, and reinforces the tags format with concrete examples (typescript, web-dev). This communicates parameter intent, not just shape.

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 opening sentence '指定した URL を Pinboard にブックマーク保存する' states a specific verb (save), resource (Pinboard bookmark), and target (URL). The purpose is unambiguous and immediately recognizable even before reading the lengthy workflow instructions. No siblings exist, so no differentiation is needed.

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 mandates an explicit three-step precondition: present a comprehensive Japanese explanation of the article, ask 'ブックマークしますか？' for confirmation, and call the tool only upon user approval. This is unusually explicit about when to invoke the tool and what gates its use, leaving nothing to inference.

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