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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: incremental fetching via a cursor and that a next_cursor is returned, which matters given there is no output schema.

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 short sentences, zero filler, with the tool's identity front-loaded and the cursor mechanics immediately after. Every clause carries information.

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 two-parameter read tool this covers the core behavior and even compensates for the missing output schema by naming next_cursor. However, 'limit' is never explained and the description calls 'since' a cursor while the schema types it as an integer, leaving ambiguity an agent must resolve on its own.

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 0%, so the description must document both parameters. It only gestures at 'since' (incrementally fetch new entries) and ignores 'limit' entirely, leaving half the parameters undocumented anywhere.

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?

States a specific verb+resource: fetching the Haven updates feed (changelog), which is clearly a read of a changelog stream. It does not explicitly differentiate itself from subscribe_updates/unsubscribe_updates in the sibling list, 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?

The description implies the polling pattern ('Pass since=<cursor> to get only new entries'), which is useful implied usage. It never states when to use this instead of subscribe_updates, nor any exclusions or prerequisites, so guidance remains implicit.

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