changes

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

With no annotations, the description carries the full burden; the word 'Return' correctly implies a read-only, non-mutating operation. However, it discloses nothing about journal retention, what happens when a cursor expires, or whether the query is resumable — behavioral facts an agent polling this endpoint would need.

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?

A single front-loaded sentence with a colon-delimited enumeration and zero filler. It is appropriately sized for the amount of information conveyed, though it stops just short of the routing detail that would make it exemplary.

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?

Output schema exists so return values need not be restated, and the description covers the delta-journal concept adequately for a zero-required-parameter read tool. What is missing is the workflow context — how this relates to wait (which also produces cursors) and how to keep polling incrementally — leaving the agent to infer the intended call pattern.

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 67% (below the 80% baseline), and kinds/limit have no schema descriptions at all. The description partially compensates by mapping the kinds enum values to plain English ('service and action transitions, detected-port changes, and configuration reloads') and by naming the cursor anchor that maps to 'since', but limit, selectors, runtime, and since_generation get no added meaning.

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 gives a specific verb+resource (return what changed in the runtime) and enumerates the categories returned: service/action transitions, detected-port changes, config reloads. That lets an agent distinguish it from a snapshot tool, but it never explicitly contrasts with siblings like wait, status, or logs, so it falls short of a 5.

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 mentions the cursor mechanism ('after a cursor') which hints at incremental polling, but there is no explicit when-to-use guidance and no mention of the obvious alternatives (wait, status, logs) that an agent must choose between. Cursor mechanics are a mechanism, not usage guidance.

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