watch

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

With no annotations, the description carries the full burden of disclosing behavior. It discloses the polling mechanism, the automatic research trigger, the NOTION_TOKEN requirement, and the stopping mechanism. However, it does not state whether the tool returns immediately, blocks, or creates side effects beyond triggering AI research, which is a meaningful gap for agent invocation.

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: it states the core purpose first, then prerequisites and stop behavior. Each sentence adds information, and the 'no need to say sync' note earns its place by preventing a misuse. Minor redundancy exists between 'polls every N seconds' and 'auto-watching', but overall it is well-structured.

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 key operational context: what is watched, what triggers research, the required environment variable, and how to stop the process. It does not describe the return value or explicitly connect research_database_id to the research trigger, but the schema covers the parameter meaning and the tool is conceptually simple enough that this is an acceptable minor gap.

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 100%, so the schema already documents all three parameters. The description adds only a loose connection ('every N seconds' to interval_seconds) and does not clarify the role of research_database_id beyond what the schema already states. Baseline 3 is appropriate.

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 uses a specific verb ('Start auto-watching') and identifies the exact resource ('Notion Watchlist'), with concrete behavior: polling for checkbox changes and keyword entries. It also distinguishes itself from siblings by noting that 'sync' is unnecessary and that 'unwatch' stops the watcher.

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?

It clearly states when to invoke the tool (to begin continuous watching) and tells the agent to call 'unwatch' to stop. It also implies an alternative ('no need to say sync') that differentiates it from sync_notion_watchlist, though it doesn't explicitly enumerate when not to use it.

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