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

Annotations already cover readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is established. The description adds genuinely valuable behavioral context beyond those annotations: cursor advancement semantics ('advances only on a real change'), data staleness ('refreshes every 6h'), and first-call behavior. This exceeds what the structured annotations alone convey.

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?

The description is dense with purposeful information, front-loading the most critical fact ('FIRST CALL, needs nothing') and an actionable first-step example. The embedded JSON-RPC whoami invocation adds bulk but serves as concrete guidance rather than filler. No sentence is wasted.

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 cursor-based incremental sync tool, the core protocol is well covered: first-call behavior, cursor echo-back, advancement semantics, change-type payloads, and data freshness. The main gaps are the absence of an output schema (return shape is unspecified) and the unaddressed relationship to whats_changed, but for a read-only, idempotent, 2-parameter tool this is largely 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 coverage is 100% — both 'limit' and 'since' are fully described in the input schema, so the baseline is 3. The description reinforces the cursor semantics with the since='0' example, which adds marginal clarity, but it does not add new parameter-level detail beyond what the schema already documents.

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 clearly states the verb and resource: returns what changed since the last call, enumerating concrete change types (prefixes added/removed, upstreams failed/recovered, records edited). However, it does not differentiate itself from the sibling tool 'whats_changed', which sounds nearly identical in scope, so it misses the sibling-distinction bar for 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 gives clear operational context: 'FIRST CALL, needs nothing', send back the cursor from the previous result, cursor advances only on a real change, data refreshes every 6h, example since='0'. But it offers no explicit when-to-use versus alternatives — notably it never addresses why one would choose changes_since over the similarly-named sibling whats_changed.

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