unwatch

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

Annotations already show readOnlyHint=false and destructiveHint=false, and the description adds valuable context: 'Nothing in the graph is deleted' and that open thesis entities remain followed. It also describes the return value ('Returns the updated watch list, as `list_watches` does'), going beyond structured data without contradicting annotations.

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?

Four sentences are tightly front-loaded: the core action first, then scope, then non-destructiveness, then return value. Every sentence earns its place with no redundancy.

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?

For a simple one-parameter mutation with an output schema and annotations, the description covers what changes, what does not change, and the return format. Nothing essential is missing.

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%, so the `entity` parameter is fully documented in the schema ('Ticker, CIK, company name, canonical key or id'). The description adds no additional meaning about the parameter, so 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 states a specific verb and resource: 'Stop watching a company you added with `watch`.' It distinguishes this tool from the `watch` sibling and clarifies the scope ('explicit watchlist only') so an agent can tell exactly what it does without opening the schema.

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 indicates the tool is the inverse of `watch` and explains that a company tied to an open thesis will still be followed, which serves as a when-not condition. However, it does not explicitly name an alternative tool for fully stopping thesis tracking, leaving a small gap in routing guidance.

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