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

With no annotations, the description carries the full burden and does well: it discloses credit cost, irreversibility, the validation gate that leaves the draft intact on failure, and the required mcp:submit permission with remediation. The only gap is the success side — it does not say what the call returns or what state the draft becomes after sending.

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 short sentences ordered by importance: what it does, cost/irreversibility, validity precondition, and auth fallback. No filler and nothing buried.

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 two-parameter mutation with no annotations and no output schema, it covers preconditions, cost, failure behavior, and permissions well. The one thing an agent would still want is what a successful send yields (confirmation or postcard identifier vs. the draft ID).

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 100% and both parameters are fully documented in the schema, including idempotency semantics, so the baseline of 3 applies. The description adds cost/irreversibility context that motivates idempotency but does not itself explain the idempotency_key parameter.

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 + resource + transition ('Send a draft postcard to production'), which cleanly separates it from create-postcard-tool, update-draft-tool and preview-postcard-tool in the sibling list. An agent can identify the terminal send step without opening any schema.

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 preconditions (draft must be complete: address, recipient, content, font_id) and the fallback path when the agent lacks permission (ask the user to review at review_url). It does not explicitly route to sibling tools such as preview or update when the draft is incomplete, leaving that inference to the agent.

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