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

Annotations declare readOnlyHint=true but idempotentHint=false, and the description usefully explains why repeated calls differ ('since you last looked', 'each is told once'). The one ambiguity is whether 'told once' means reading consumes/marks items as delivered, which would be a side effect worth clarifying against the read-only hint — but it reads primarily as a cursor-style feed, not a contradiction.

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?

Two tight sentences with the core delta semantic front-loaded and a dense but non-redundant enumeration of item types. 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?

For a single-parameter read-only feed with no output schema, the description gives enough to know what comes back and why repeated calls differ. Minor gaps remain: item ordering, whether anything is consumed, and how to re-read history, none of which are covered elsewhere.

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 description coverage is 100% and the single 'project' parameter is fully documented (name or id, defaults to all projects). The description adds nothing about scoping the news feed to a project, so the baseline 3 applies.

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 concretely enumerates what the tool returns — human answers and edits, other agents' claims, ticks, notes, and messages — which is far more informative than the opaque name 'news'. It conveys a delta/changelog semantic ('what changed since you last looked') that differs from static siblings like list/view, though it never names those siblings to sharpen the distinction.

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?

'Since you last looked' and 'each is told once' imply the calling pattern: call it to catch up, and items won't repeat. However, there is no explicit when-to-use/when-not-to-use guidance, no mention of alternatives such as list or view, and no statement of how often to call it.

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