summarize_cluster

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

With no annotations provided, the description fully discloses behavior: it invokes an LLM CLI (claude, codex, gemini with override), can write to Obsidian and Zotero when apply=True, returns JSON by default, and saves a prompt file if CLI is missing. The return structure is also described.

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 front-loaded purpose statement, followed by mode details, usage cues, and fallback instructions. It is concise but could trim some procedural repetition (e.g., re-explaining the apply flow).

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 the main workflow, fallback, and return format, but does not explain the individual write flags or any prerequisites like how to obtain a cluster_slug. Given the tool's complexity and lack of schema descriptions, it is largely complete but has minor gaps.

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 description coverage is 0%, so the description must compensate. It explains 'cluster_slug' and 'llm_cli' verbally, and mentions 'apply' behavior, but does not describe the boolean parameters 'write_zotero' and 'write_obsidian', leaving their purpose unclear. Partial coverage across 5 parameters.

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 starts with a clear action: 'Generate per-paper Key Findings + Methodology + Relevance via LLM CLI.' It specifies the resource ('cluster_slug') and distinguishes from sibling tools like 'apply_cluster_summaries' and 'ask_cluster' by detailing the generation process and output modes.

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 explicitly states when to use the tool: when user says 'summarize this cluster's papers', 'fill the TODO Findings', or after 'auto' ingest. It also provides an alternative path: if no LLM CLI is available, the prompt is saved and can be processed with 'apply_cluster_summaries' or the CLI re-run.

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