create_watch

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

The description explicitly states that the tool mutates and describes get-or-create semantics. It mentions API key requirements. However, it does not describe the return value or potential side effects beyond creation, such as what happens if no matches are found. Given no annotations, the description carries the full burden but still misses some behavioral context.

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 lengthy but well-structured with clear sections. It is front-loaded with the main purpose and efficiently covers all necessary details. Minor redundancy (e.g., mentioning both forms) but justified by complexity.

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?

Given the tool's complexity (11 parameters, nested objects, no output schema), the description provides rich context: usage guidelines, behavioral quirks, and parameter interrelationships. The main gap is the lack of description about the return value or success/failure conditions.

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 input schema already describes all parameters (100% coverage), but the description adds significant meaning: it explains the two forms, the precedence of criteria, the role of novelty_min as a signal/noise knob, and the structure of criteria with examples. This greatly enhances agent understanding beyond 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 that the tool creates a standing watch evaluated daily against newly-indexed papers, surfacing matches via email digest and check_watches. It distinguishes itself from sibling tools like preview_watch and update_watch by mentioning their roles.

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 provides explicit guidance on when to use this tool (e.g., for creating watches) and when to use alternatives (e.g., use preview_watch first to tune criteria, edit with update_watch). It explains the get-or-create behavior and the precedence of criteria over legacy seeds.

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