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

Annotations already declare readOnly, non-destructive, closed-world, so the safety bar is low. The description still adds real value beyond them: results are deduplicated and incremental, only unmuted subscriptions are returned, and membership is rechecked on every read (i.e., permissions can shrink between calls). That last point is exactly the kind of behavioural nuance annotations cannot express.

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, front-loaded with the resource and immediately followed by the operational instruction. No filler, though the cursor sentence is compressed to the point of ambiguity rather than clarity.

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?

No output schema exists, so the description should clarify the return shape; it says 'change IDs' and implies a next_cursor but does not state ordering, termination, or what a deduplicated incremental page contains. For a zero-required-param polling tool that is the minimum viable level, not complete.

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 carry all three parameters and largely doesn't. 'Resume next_cursor' never says that the cursor is supplied via the `since` parameter, and `limit` (1-100, default 30) is entirely unexplained. Only `thread_id` is obliquely covered by 'one accessible thread'.

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 concrete resource (incremental, deduplicated change IDs) and two modes: all unmuted subscriptions, or a single accessible thread. An agent can tell this is a collaboration change-feed, distinct from collaboration_messages or collaboration_threads. It stops short of naming the nearby sibling get_changes, so the differentiation from that tool is left implicit.

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?

'Resume next_cursor' and 'or one accessible thread' imply the two usage modes (poll continuation vs. single-thread scope), but guidance is only implied. There is no statement of when to pick this over get_changes, nor any prerequisite for the first call when no cursor exists.

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