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

Annotations already declare readOnly, idempotent, non-destructive, openWorld, so the safety profile is covered. The description adds genuinely new context beyond annotations: content is untrusted (a prompt-injection caution) and a polling rate limit of 30 seconds, both of which an agent needs for correct behavior.

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?

Three short sentences, purpose front-loaded, each one earning its place: what it does, a trust warning, and a rate limit. No filler or repetition.

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 read-only tool with full annotation coverage, a fully-documented 2-param schema, and no output schema, the description covers the remaining essentials (trust boundary and polling cadence). Nothing required to invoke it correctly is missing.

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 description coverage is 100%, so accessKey and reference are already fully documented (including the 'retain and reuse for identical retries' and 'never the owner key' notes). The description only restates 'conversation key' and adds nothing new beyond the schema, so the 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?

Specific verb+resource: 'Read your private proposal and messages using its conversation key' tells the agent exactly what it retrieves and the access mechanism. It distinguishes itself conceptually from siblings like read_board and get_booking_info via 'private proposal' and 'conversation key', though it never names an alternative explicitly.

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?

The description gives one operational rule ('Poll at most every 30 seconds') but no guidance on when to prefer this over reading the board or other message-retrieval tools. Usage is implied by the resource name rather than stated, leaving the agent to infer the context.

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