What's new

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

Annotations declare readOnlyHint=false and idempotentHint=false, which is counterintuitive for a "what's new" read; the description resolves this by disclosing that a call without `since` mutates the bookmark and advances it, while `since` leaves it untouched. That is a state-changing side effect made visible, not restated.

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?

Three sentences, no filler: what it returns, when to call it, then the since/bookmark fork. Front-loaded with the payoff and the branch condition comes before the agent needs it.

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 carries the return-value burden and does enumerate the result categories. Gaps are minor: no ordering, pagination, or volume expectations for what could be a large diff.

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 param definitions already carry their own weight; the description adds the interaction semantics — bookmark read-and-advance versus fixed window — that no single field description conveys. It adds modest extra value on `projectId` binding beyond the schema's 'optional if a project is bound'.

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?

Names a specific resource-level question ('what changed on a project since you last looked') and enumerates the payload: new threads, replies grouped by thread, resolutions/defers, assignments and mentions. No sibling tool overlaps this diff-style read, so it's trivially distinguishable.

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?

"Call it at the start of a session" gives an explicit trigger condition, and the second sentence draws the since-vs-bookmark decision boundary with the consequence of each choice. That is exactly the when-to-use guidance an agent needs.

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