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

Annotations only give idempotentHint and destructiveHint, so the description must carry the rest, and it does: login is required, the full review consumes LLM spend and is cached (warns against duplicate calls), and member anchors can be continued from the result. It also warns about semantic false negatives ('warming empty does not mean nobody'), which is the kind of trap an agent cannot infer from schema or annotations.

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?

Every clause carries routing or cost information and the prerequisite plus primary action are front-loaded, with no filler sentences. The tradeoff is extreme compression: semicolon-chained fragments with no explicit subject ('warming空非无人', 'claimed=false仅看siteUrl不能开聊') are terse to the point of being hard to parse on first read.

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 tool relies on the description, and it does supply result-field semantics (source=inferred, placed, claimed, warming, supply none/gated/warming) that would otherwise be opaque. The remaining gap is that these status fields are named without explaining what each value means for the agent's next action, beyond the two cases that get an explicit handoff.

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%, so the baseline is 3. The description restates the metadataOnly tradeoff that the schema already documents in nearly the same words ('fast, saves money, for probing direction'), and subjectId/subjectType defaults are left entirely to the schema. It adds little meaning beyond the structured fields.

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 opening clause states a specific verb and resource: read your own / your product's chain position plus upstream and downstream relations. The anchor-node framing and the explicit routing clause to siblings (list_my_chain_anchors, list_chain_group_members, set_my_chain_position) make it distinguishable from neighbors. It stops short of 5 only because the telegraphic phrasing forces the agent to parse several compressed clauses before the core purpose is fully clear.

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?

Explicitly states the prerequisite (call list_my_chain_anchors first to get an anchor), the cheap-vs-expensive mode choice (metadataOnly=true for direction probing; the full relation review costs money and is cached, so don't repeat), and the handoff conditions (groupId/direction/profileVersion → list_chain_group_members; placed=false → set_my_chain_position). Both when-to-use and when-to-use-something-else are named.

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