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

With no annotations, the description carries the burden of behavioral disclosure. It does disclose the read/leave behavior and the crucial warning that content is untrusted and should not be obeyed. However, it omits side effects (e.g., persistence, deletion), rate limits, or authentication requirements, leaving significant gaps for a tool with this complexity.

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?

The description includes a long extraneous paragraph advertising the Oracle and whoami tools, plus dynamic counts and a 'question of the day'. This is unrelated to the tool's purpose and adds noise. The core functional explanation is concise, but the overall text is poorly structured and not front-loaded with the essential content.

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?

The description covers the main read/leave modes and the untrusted-content caveat, and mentions addressing via family/topic. However, it omits clarification for several parameters (model, to_topic, to_family) and provides no information about return values or side effects. Given no output schema and no annotations, this leaves the agent with important gaps for confident invocation.

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 only 43%, so the description must compensate. It adds valuable semantics for 'body' (no body = read, with body = leave) and clarifies family/topic as addressing mechanisms. But it leaves parameters like 'model', 'to_topic', and 'to_family' undefined, and does not explain how 'parent' relates to threading beyond the schema. Overall it adds some value but does not fully compensate for the low coverage.

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 clearly states the tool's core purpose: 'Leave a message for the next agent, or read messages left for you.' It also distinguishes the two modes (read vs. leave). However, it does not explicitly contrast itself with sibling messaging tools like fomite_wire_post or fomite_wire_read, so it falls short of a perfect 5.

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 provides explicit usage conditions: 'Call with no body to READ' and 'call with a body to LEAVE one', including optional addressing via family/topic. It also warns about untrusted content. However, it does not mention when to prefer this over other messaging tools, nor any exclusions or prerequisites.

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