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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real context: what stops is only future discovery, while already-found results remain visible in get_tender_updates. It also discloses the Winquill account requirement. It does not explain reversibility (restarting via watch_tenders), which keeps it below 5.

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?

Front-loaded with the usage trigger and packs effect, prerequisites, and an example into a few clauses without waste. The semicolon-chained sentence is dense but readable; nothing extraneous.

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?

Covers trigger, id provenance, post-stop behavior, and account prerequisite, and an output schema exists so return values need not be described. An agent has everything needed to invoke it correctly.

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% and the schema already documents watch_id's provenance, so the description mostly repeats it. The example {"watch_id":"wch_abc123"} adds a useful format cue, but no constraints or edge cases 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?

States a specific verb and resource ("stop one of their Winquill watches") and identifies the exact input key (watchId) plus where it comes from. It is clearly distinguishable from watch_tenders, list_watches, and get_tender_updates, which are all named.

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?

"Use this when the user wants to stop one of their Winquill watches" gives an explicit trigger, and the provenance hint routes the agent to watch_tenders or list_watches to obtain the id. No explicit when-not is stated, but the note that existing findings still appear in get_tender_updates implies the boundary against continuing to monitor.

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