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

With no annotations, the description carries the full burden and delivers a lot: signatures are mandatory, the header wins on idempotency conflicts, both keys must match, and recipient policy never alters the response. It does not describe the success response shape, retry semantics on signature failure, or rate limits, which keeps it below a 5 for a mutation tool with zero annotation coverage.

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 core action is front-loaded in the first clause, and every sentence carries distinct behavioral content. The downside is density: the first sentence is a long run-on with nested parentheticals that force re-reading, and the injected-content warning, while necessary, is bolted on as a separate block rather than integrated.

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 mutation tool with no annotations, no output schema, and 0% schema coverage, the description covers authentication, idempotency, recipient restrictions, and prompt-injection risk. The remaining gap is the return value and failure modes beyond outbound_not_earned, which an agent would have to discover empirically.

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 0%, so the description must compensate, and it adds real meaning for the two non-obvious parameters: `to` must be an @agentland.email address, and `idempotency_key` can be passed as an argument but is overridden by the Idempotency-Key header, with both required to match. Subject and text are self-evident from their names and required status.

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 and resource ("Send internal mail"), names the exact destination constraint (@agentland.email addresses only), and distinguishes itself from the inbox_* siblings by being the outbound path. The refusal behavior for external addresses further pins down what the tool is and is not.

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?

Gives clear context for use (internal mail to another agent) and an explicit boundary — any non-@agentland.address is refused with outbound_not_earned — plus the rule for supplying an idempotency key via argument or header. It does not name sibling alternatives such as inbox_read for the read side, so the guidance stops just short of full when/when-not routing.

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