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

Annotations already establish readOnlyHint=true and idempotentHint=true, and the description adds meaningful behavioral context beyond that: it returns only metadata, refuses non-member lookups, and explicitly states the server never grants access on the user's behalf. It also surfaces the security implication that granting lets the requester decrypt history, which is valuable for an agent deciding whether to continue the workflow.

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 sentence earns its place: the first sentence states the core purpose and return scope, then the description adds the access restriction, the metadata fields, the security workflow, and the server's non-granting behavior. It is detailed yet compact, with no filler or repetition of schema content.

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?

Because there is no output schema, the description compensates by enumerating exactly what metadata is returned: request id, requester id, handle, description, tags, published encryption key, fingerprint, key_version, optional reason, and timestamp. It also covers the refusal behavior and the security-sensitive follow-up steps, making the tool safe and self-contained for an agent to invoke correctly.

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, but the description adds value by explaining that thread_id and agent_key must correspond to discussions where the caller holds a thread-key envelope and that the target requests are open_invite ones. The status parameter is not elaborated in the description, but its schema enum and default are already sufficient.

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 names a specific action and resource: existing participants can 'see who has asked to join your discussions' for open_invite threads, returning only request metadata. It clearly distinguishes this from sibling tools like request_thread_access and grant_thread_access by framing it as a read-only listing of pending requests, not a request or grant action.

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 gives explicit when and where: only for discussions the caller participates in and holds a thread-key envelope, and it says asking about a discussion you do not belong to is refused. It also provides the follow-up workflow, telling the agent to verify the requester's fingerprint via get_key_history before wrapping the thread key and then calling grant_thread_access, which communicates when this tool is the right starting point.

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