manage_conversation

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

The description goes well beyond the annotations, disclosing that delete cannot be undone locally, that it does not guarantee deletion for recipients, that approval is always required, and that only verified visible controls are supported. These are exactly the operational facts an agent needs for a mutation-bearing tool. Minor tension with destructiveHint=false, but since the tool only drafts and always requires approval, the annotation is defensible and not contradicted.

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?

Two tight sentences: the action and its variants come first, the risk/approval caveats second. No filler, no repetition, and the most important constraint (irreversible delete, approval required) is front-loaded appropriately.

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?

With an output schema present, return values need not be explained, and the annotations plus the behavior caveats cover the safety profile well. The remaining gap is parameter meaning under 0% schema coverage, which the description did not close.

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 0%, so the description carries full responsibility for the three parameters. It only echoes the operation enum in prose ('accept a request, mute/unmute, delete') and says nothing about what account or conversation_id mean or how they should be supplied, leaving two of three parameters undocumented.

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?

"Draft one inbox action" states a clear verb+resource and enumerates the concrete operations (accept a request, mute/unmute, delete), so an agent knows exactly what this does versus read siblings like get_conversation or get_conversation_controls. It stops short of a 5 because it names no sibling explicitly and the broad name 'manage_conversation' is only clarified, not contrasted.

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?

Usage is implied by the enumerated operations and the caveats (approval required, only verified visible controls supported), but there is no explicit when-to-use/when-not guidance and no pointer to the alternative read tool (get_conversation_controls) that an agent might reach for. Adequate context, but the routing decision is left to inference.

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