summarize_cluster

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

With no annotations, the description fully discloses behavior: it invokes an LLM CLI, returns JSON by default, writes to Obsidian and Zotero when apply=True, handles missing CLI by saving a file, and describes the return object fields. No contradictions.

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 well-structured with a clear summary line, detailed behavior, usage guidance, fallback, and return type. It is moderately concise but could be slightly tighter by integrating parameter descriptions more directly.

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 covers all aspects: purpose, all parameters (implicitly), usage context, fallback, and return value. It is complete for the tool's complexity, especially given the presence of an output schema.

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?

The description adds meaning for cluster_slug, llm_cli, and apply by explaining their roles and defaults, but write_zotero and write_obsidian are not explicitly described beyond the overall write-back statement. Given 0% schema coverage, the description compensates well but misses explicit mention of two boolean flags.

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 generates per-paper Key Findings, Methodology, and Relevance via an LLM CLI, specifying the action on a cluster. It distinguishes itself from siblings like brief_cluster and ask_cluster by detailing its write-back behavior and fallback mechanism.

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?

Explicit when-to-use examples are given ('summarize this cluster's papers', 'fill the TODO Findings') and alternatives are provided, such as the fallback to a saved prompt and the apply_cluster_summaries tool if no LLM CLI is available.

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