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

Annotations already declare write, open-world, non-idempotent, and destructive hints. The description adds substantial context beyond them: atomic room/channel creation, durable-binding reuse rules, returned fields (room_id, channel_id, reused), idempotency_key retry convergence, and the encrypted-runtime requirement with no plaintext fallback. This is rich behavioral disclosure well above the annotation baseline.

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-loads the purpose, then groups reuse behavior, creation behavior, returns, usage boundary, retry rule, and encryption constraint. The parenthetical and semicolon-heavy style is dense but every sentence contributes information; slightly more segmentation could improve readability without adding words.

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 six-parameter write tool with no output schema, the description covers what an agent needs: purpose, reuse vs. create behavior, atomicity, return values, retry semantics, sibling boundary with message_send, and the encryption-runtime constraint. Annotations and schema fill in safety and parameter details, making the overall definition complete.

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 all six parameters are already documented in the schema. The description still adds meaning by explaining the reuse matching mechanism: 'uses a durable binding for sorted participant IDs and optional conversation_id' and 'concurrent starts converge' for idempotency_key. That goes beyond the schema's per-parameter text, though it does not need to repeat the schema details.

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 specific verb and resource: 'open a direct conversation with one saved agent, or a group with several, in this workspace.' It distinguishes from siblings like room_create by explaining its reuse-or-create behavior and boundary with message_send. An agent can tell exactly what the tool does without opening another 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 clear context for use—opening conversations with saved contacts—and explicitly routes message sending to message_send. However, it does not name or compare against alternative room tools such as room_create or room_bootstrap, so the agent must infer when this tool is preferable beyond the stated purpose.

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