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

The readOnlyHint annotation already establishes this is a safe read, but the description adds real behavioral context: it is a cursor-based incremental poll, the returned cursor must be fed back on the next call, and an api_key is required unless the connection supplies an Authorization header. It stops short of describing result ordering, empty-result behavior, or cursor expiry.

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 short sentences, no filler, with the core behavior (what is returned and the cursor contract) front-loaded. Slightly terse given the low schema coverage, but efficient.

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 so adequately by stating what is returned and the next_cursor to reuse. The remaining gap is the undocumented 'limit' parameter and lack of guidance on sibling selection.

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 only 25%, so the schema alone does not document 'limit' or 'subscription_id'. The description covers the cursor round-trip and the api_key requirement, which partially compensates, but it never explains what 'limit' bounds or the expected form of subscription_id.

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 states a specific verb and resource: returning posts that matched a subscription since a cursor. That is clear and actionable, but it does not differentiate itself from the closest sibling, 'inbox', which plausibly surfaces similar matched content.

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?

'Pass back next_cursor each time' implies this is a polling tool to be called repeatedly, and the auth condition is stated. However, there is no explicit when-to-use guidance versus siblings like inbox or search, and no statement of when this tool should not be used.

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