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

Annotations only give the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true). The description adds genuinely useful behavior beyond that: login is required, writes run in preview by default, update treats omitted fields as no-change and null as clear, and confirm re-verifies the caller's permissions server-side. Return format and rate limits are not described, but that is minor against annotation coverage.

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?

A single dense paragraph with the login prerequisite front-loaded (【需要登录】) and op semantics separated by semicolons. It is compact for a nine-op, eleven-param tool and every clause is load-bearing, though the density makes it harder to scan than a structured list would be.

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 multi-op tool with 11 params, no output schema, and a nested fields object, the description covers the operation set, the update/patch semantics, and the preview-then-confirm workflow. Gaps remain around the id/kind parameters and what list returns, but the description is largely complete for correct invocation.

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 parameters, and it does for most: it explains fields semantics (omitted vs null), set_role using userId and role (ADMIN/INVITER/null for groups, add for venues), feature using the featured flag, and the previewHash/consent/preview commit contract. The id and kind parameters are not explicitly documented, which keeps this from being a 5.

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 enumerates each op with a specific meaning (list reads own resources, create/update public profile, pause/unlist/relist status, confirm, set_role grants/revokes admin, feature organizes recommended groups), so an agent can tell what the tool does across its nine operations. It is clear on scope (本人/own resources) but never names a sibling tool, so routing against the many community-resource siblings is left to inference.

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 explains when each op applies and describes the write workflow (writes default to preview; confirm requires same params plus previewHash with consent=true and preview=false), which is concrete usage guidance. It does not, however, address when to choose this tool over alternatives such as draft_community_resource or contact_community_resource.

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