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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), so the bar is lower. The description adds useful context beyond annotations: threads link to an inquiry or booking, unanswered_only ties to response rate, pagination via next_cursor, and the Cotlet API key auth requirement.

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 resource and scope, with the alternative-parameter guidance next. Slightly redundant between the first fragment and 'Lists your Peerspace inbox threads,' but overall every sentence contributes and it stays compact.

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 paginated list with no output schema and fully-documented params, the description covers what the tool returns (last message time, last-writer flag), threading model, pagination, and auth. Nothing critical for correct invocation 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 coverage is 100%, so the baseline is 3. The description adds genuine meaning for unanswered_only (guest wrote last / response rate measurement) and cursor (pass next_cursor back for the next page), reducing ambiguity beyond the schema's terse field docs.

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 (Lists) and resource (Peerspace inbox threads) and even previews the payload (last message time, whether the guest wrote last). An agent can tell this apart from peerspace_get_conversation without opening the 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?

Explains the key branch parameter: 'Set unanswered_only to get only threads where the guest wrote last, which is what response rate is measured on.' This gives clear context for one option, but does not explicitly route the agent away from siblings like get_conversation or send_message.

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