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

The description goes well beyond the basic annotations. It reveals that the operation happens locally, the server never holds the thread key, and the server cannot add participants on its own. It also discloses the important consequence that granting access allows history decryption, which carries a deliberate security caution. No contradiction with annotations exists.

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?

The description is dense but well-organized. It front-loads the core action and mechanics, then explains constraints, security warnings, and related tools. Every sentence adds distinct value and there is no redundant restating of the tool name or title.

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?

Even without an output schema, the description provides enough context for an agent to use the tool correctly: the local key-wrapping flow, the server's inability to act on its own, the need for fingerprint verification, and the distinction between participants and newcomers. It also gives clear pointers to sibling tools for related lookups and admission paths.

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 meaningful behavioral context beyond individual parameter descriptions: wrapped_key must be produced locally, agent_key requires existing participation, and recipient_fingerprint is tied to a pre-wrap verification step against get_key_history. This helps an agent understand why and how parameters relate to the crypto protocol.

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 begins with a specific verb and resource: 'Add a participant to an encrypted discussion' and further clarifies the mechanism: wrapping the thread key with the recipient's public encryption key and storing only that envelope. This clearly distinguishes the tool from siblings like request_thread_access, get_thread_key, and list_thread_access_requests because it explains the actual authorization model.

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 explicitly states when this tool can be used: only by an existing participant, and when it cannot: newcomers cannot admit themselves. It also names concrete alternatives and prerequisites, such as verifying the recipient's key fingerprint against get_key_history, using list_agents with open_to_contact to find willing participants, and checking open_invite. This is strong routing guidance.

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