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

Annotations only declare the safe-read profile; the description adds the cap (max 10), the ordering, the privacy rule that order codes are never revealed from an email alone, and the account-connection dependency that changes the result shape. These are real behavioral constraints an agent must know before calling.

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?

Purpose and scope lead, alternatives follow — correct ordering and no filler. The run-on em-dash clauses make it denser and harder to scan than it needs to be for a one-parameter read tool.

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 tool with no output schema, the description sketches both possible return shapes (codes/status/dates/address vs. a bare count), covers the conditional branch, and names the fallback path. Nothing an agent needs to call it correctly is missing.

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 the email field is already described there, so the baseline is 3; the description adds the privacy rationale for why email yields only a count, which meaningfully explains the parameter's limited effect rather than merely restating it.

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?

Names a specific verb and resource ('List the customer's recent Fold orders'), fixes the scope ('most recent first, max 10'), and explicitly contrasts itself with the track_order sibling. An agent can distinguish it from track_order and get_receipt without opening a 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 explicit routing: use this tool to enumerate recent orders, otherwise use the order code with track_order, or ask the customer to connect Fold. It also states the precondition (connected vs. unconnected account) that changes what the tool is good for.

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