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

Beyond the idempotentHint/destructiveHint annotations, the description discloses auth requirements, the mandatory confirmation step, and — most valuably — the snapshot semantics (contact data is frozen at acceptance time and does not follow later profile edits). It also explains idempotency scope ('repeat of your own request') and maps the specific error codes an agent must branch on, which the annotations cannot 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?

Dense and largely front-loaded, with no filler sentences, but the semicolon-and-arrow telegraphic style packs prerequisites, error routing, and workflow into one undifferentiated block. '先明确确认' is unclear — there is no confirm parameter, so the reader must infer a conversational confirmation step. Brevity here comes partly at the cost of parseability.

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 single-parameter mutation with no output schema, the description covers everything an agent needs: auth precondition, required own-side data, the exact branching for each error code, the recommended pre-read tool, and the post-acceptance snapshot guarantee. No material gap remains.

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% and the single conversationId parameter already documents the 1-1-only constraint, so the schema carries the load. The description's '真人DM' phrasing reinforces that restriction but adds no new syntax, format, or lookup guidance beyond the schema text; baseline 3 applies.

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?

States a concrete verb and resource — send a contact-exchange request over a real-person DM in a 1-1 conversation — and explicitly names the siblings it is not (add_profile_link, respond_contact_exchange, get_contact_exchange_state). An agent can distinguish it from the accept/list counterparts without inspecting any schema.

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?

Gives prerequisites (must be logged in, must have at least one contact method of your own), an explicit routing rule per failure state (no_contact_info → add_profile_link; already_exchanged → do not retry; peer_request_pending → respond_contact_exchange), and an ordered workflow (get_contact_exchange_state → confirm → request). When-to-use and when-not-to-use are both covered.

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