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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context: reading never triggers a poll, is never charged, and the id acts as a capability. This goes beyond the annotations, but the description also includes unrelated feedback promotion, which slightly dilutes transparency. No contradiction with 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?

The description includes a significant promotional paragraph about POST /feedback that is unrelated to the tool's function. This adds noise and reduces conciseness. The core function is explained in the first two sentences, but the extra content makes it less efficient.

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 read tool with one parameter, the description covers the return state (active, matched, expired) and the observation that matched. It also explains the capability aspect and the free/non-polling behavior. Although there is no output schema, the description sufficiently describes the return information. The unrelated feedback content does not hinder completeness.

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 describes the id as 'The watch id returned by watch_register.' The description adds semantic meaning by explaining the id is a capability, which is important for understanding how it can be transferred. This goes beyond the schema's basic description.

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 the tool reads the current state of a registered watch (active, matched, or expired) and returns the matching observation. It implicitly differentiates from watch_register by focusing on the read operation, and the verb+resource is specific.

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 explains when to use this tool (to check a watch's state) and provides context about the id being a capability that can be passed to a successor process. It also notes reading is free and non-polling, but does not explicitly contrast with sibling tools like watch_register or others. The guidance is clear but lacks explicit exclusions.

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