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

With no annotations, the description carries the full burden and does so well: auth requirements (connector OAuth or private Bearer), a size cap (16,384 UTF-8 bytes), a rate limit (30 new messages per sender per minute), idempotency retry semantics, and a return caveat that acceptance doesn't prove reading or execution. This is exactly the non-obvious behavior an agent needs.

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?

Four tightly packed sentences, each carrying a distinct fact (auth, limits, retry, return semantics), and the core action is front-loaded. Nothing is wasted and there's no redundancy.

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?

No output schema exists, so the description must cover return behavior; it does, explaining that a signed acceptance receipt is returned and that acceptance doesn't imply reading or execution. Combined with limits, auth, and idempotency, an agent has everything needed to call it correctly.

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 only 33% (only handle is documented). The description compensates by clarifying the body byte limit as UTF-8 bytes and, crucially, explaining clientMessageId's idempotency purpose ('Reuse clientMessageId with identical recipient/body after a timeout'), which is absent from the schema. It adds real meaning beyond the structured fields.

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 (Send) and resource (a message to a handle), making the action unambiguous. It doesn't explicitly contrast itself with a sibling like agent_inbox, but no sibling clearly overlaps as a send operation, so differentiation is implicit rather than stated.

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 rather than spelled out: the tool sends messages, so an agent infers when to call it. It offers auth-method and retry guidance, but never states when to prefer this over alternatives or any exclusion conditions, leaving usage largely to inference.

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