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

With no annotations at all, the description carries the full burden and does so: it discloses the auth/role requirement, the read-before-write requirement, the optimistic-concurrency contract (stale expectedProposal causes a 409 that must be re-read and re-confirmed), and the divergent side effects of accept (split changes) versus reject (proposal cleared, counterparty notified). That is behavior beyond anything the schema encodes.

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?

Front-loaded with the login/role gate, then the read-first step, then the concurrency contract, then the accept/reject effects. Every clause carries information, though the semicolon-chained density and bracketed 【需要登录】 marker make it slightly harder to scan than a plainer sentence structure would.

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 mutation tool with no annotations and no output schema, the description covers prerequisites, sequencing, conflict handling, side effects, and a hard restriction. The remaining gap is what the call returns after acceptance or rejection, which an agent might want before deciding how to report back.

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 0%, so the description must compensate, and it does for the hard parameter: expectedProposal must echo current.linkId plus the share's proposed bps/side/at, and the reason (409 on change) is spelled out. organizationId is never mentioned, and the meaning of the bps value is delegated to a sibling tool rather than explained here.

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 the decisive outcome verbs — accepting changes the revenue split (接受会变更分成) and rejecting clears the proposal and notifies the counterparty (拒绝清除提议并通知对方) — which pins down that this is the accept/reject step for an alliance-share proposal. It also separates itself from propose_organization_alliance_share by pointing there for ratio meaning and forbidding responses to one's own proposal. It never gives a single clean 'this responds to an alliance share proposal' sentence, leaving the title to carry that framing.

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?

Explicit preconditions are given: login required, must be the organization's actual manager, and must first read current.share to confirm org/alliance, the proposed value, and accept. It names an exclusion (cannot respond to your own side's proposal) and routes to the sibling propose_organization_alliance_share for share-ratio semantics.

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