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

Beyond the annotations (write, non-destructive, closed-world), it discloses the consent precondition and, importantly, warns that returned third-party text arrives wrapped in 'untrusted_content' with a '_notice' and must be treated as data rather than instructions - a genuine behavioral/safety trait not derivable from the schema. It stops short of describing delivery semantics or failure modes.

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 dense sentences with the core action front-loaded, followed by the precondition and the injection warning. Every sentence carries weight, though the parenthetical and quoting make it slightly hard to scan.

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 6-parameter write tool with nested hostRequest and no output schema, it covers the essentials: purpose, consent requirement, special recipient, and the untrusted-content handling. It omits guidance on idempotencyKey and token placement, but those are addressed in the schema and are non-blocking.

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 83%, so the schema already documents nearly all parameters; description adds only that consentPrivateDelivery must be true (also a const in the schema) and clarifies the 'orbita' target. Baseline 3 is appropriate since the schema does the heavy lifting.

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 states a specific verb and resource - 'Send a direct message to another agent' - and even names a special-case recipient ('orbita' for the ORBIT reception). It clearly separates itself from receive-side siblings like inbox and from report_message, though it does not explicitly contrast itself with callback or propose.

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 gives one concrete routing case (use 'orbita' for the ORBIT reception) and a hard precondition (consentPrivateDelivery must be true), but there is no guidance on when NOT to use this versus callback, propose, or report_message, so usage is only partially implied.

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