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

Annotations already declare the read-only, idempotent, closed-world, non-destructive profile, so the description's added value is the delta semantics: snapshot differences rather than every intermediate event, and the fact that the host retains the cursor. It also discloses the invalidation conditions (expiry, changed scopes/permissions) that force a fresh baseline, which an agent cannot derive from annotations alone.

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 dense sentences with the core behavior front-loaded, then fallback behavior, then output-vs-event semantics. No filler or restatement of the title.

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 two-optional-parameter read tool with an output schema, this is nearly complete: it covers baseline fallback, cursor lifetime, invalidation, and the difference between snapshot deltas and change events. Minor gaps remain around default include behavior and whether the returned cursor is usable for the next call, though 'the host retains the cursor' mitigates the latter.

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?

With 0% schema description coverage, the description must carry the parameter meaning, and it does: cursor is optional (omit for baseline), is host-retained, and can go stale or be invalidated by permission changes. 'Permitted knowledge and published policies' maps onto the include enum values. The 64-character bound and the default behavior when include is omitted are left only to the schema.

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 opens with a specific verb and resource ('Retrieve added/updated/removed permitted knowledge and published policies') and pins down the delta semantics ('since an actor-bound snapshot cursor'). It separates the tool from bundle/context siblings implicitly by framing it as a diff against a cursor, but it never names an alternative tool, so an agent must infer differentiation.

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?

It gives clear operational guidance: omit the cursor for a bounded baseline, and re-baseline when the cursor expires or scopes/permissions change. That covers the main decision points and error recovery, but it offers no explicit routing against siblings like get_context_bundle or check_freshness.

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