Doco Changes

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

Annotations already cover readOnly, idempotent, and non-destructive. The description adds meaningful context by explaining the two-phase behavior (manifest+cursor first, then added/removed/modified/moved) and the sync_required flag's implication, which is valuable beyond the annotations. It doesn't describe error or rate-limit behavior, but the core incremental pattern is well disclosed.

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 sentences, both information-dense and front-loaded. The first sentence explains the core concept (watermark establishment and incremental reads) with a clear mode split. The second sentence encodes the critical behavioral rule. No filler or repetition.

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?

Given an output schema exists and annotations cover safety, the description sufficiently explains the tool's stateful behavior and how to use it correctly. The only minor gap is that it doesn't explicitly define what happens if 'after' is missing on a second call, but the phrase '首次不传' implies the convention clearly.

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 100%, so the schema documents all parameters. The description adds usage-level meaning (first call omits after, subsequent calls use cursor) that complements the schema's generic 'opaque cursor' description. However, it doesn't add detail beyond what a careful agent could infer from the schema plus the description.

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 tool establishes or incrementally reads block-level change watermarks for documents. It distinguishes the two modes (initial manifest/cursor vs. subsequent cursor-based diff) and references sibling tools by indicating a re-read of content is required when sync_required=true, which differentiates it from doco_read or doco_get_blocks.

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 explicitly tells when to omit 'after' (first call) and when to pass 'cursor' (subsequent calls). It also provides a critical conditional: if sync_required=true, the agent must re-read the document body and establish a new baseline, which is a clear instruction on what to do next rather than just what the tool does.

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