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

Annotations already cover safety (readOnlyHint, destructiveHint=false, openWorldHint=false), and the description adds non-obvious context the annotations cannot: an auth header is required and polling should be paced at ~5 minute intervals. The caveat that events are public incident records with evidence links, not live reachability checks, and that disruptions are not evidence of censorship, meaningfully guards against misinterpreting results.

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 short sentences, each carrying distinct load: what it returns and in what order, then auth, then cursor/cadence mechanics, then the semantic caveat about what the data means. The scoping information is front-loaded with no filler.

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?

With no output schema, the description does take on explaining return content (public incident records with evidence links) and pagination mechanics (cursor 0 at first, pass next_cursor onward). It leaves a small gap on how polling terminates — whether next_cursor is absent or null at the end of the feed — and never defines the limit parameter.

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 50%: cursor is documented in the schema, limit (1–50) is not documented anywhere. The description reinforces the cursor round-trip but calls it "next_cursor" while the parameter is named "cursor", and says nothing about what limit controls. Baseline 3 is appropriate given the partial coverage and the unchecked limit parameter.

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?

"Read your watch feed after a cursor, oldest first" gives a concrete verb (read), a specific resource (watch feed), and an ordering guarantee. It is clearly distinct from siblings like watch_list and voidly_alert_poll in behavior, though it never names an alternative to disambiguate explicitly.

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 states the operational prerequisites and cadence directly: send X-Agent-Key in the header, pass next_cursor back on each call, poll roughly every 5 minutes. That is real when-and-how guidance, but it gives no exclusions or pointers to watch_add / watch_list / voidly_alert_poll for adjacent tasks.

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