shopfetch

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety bar is low. The description still adds real behavioral value: it discloses the verdict semantics ('says Barcode verified only when it is, with what was verified, where, when and under which rules') and an important scope limit ('Price and stock are never taken from the record'). It does not describe failure output on a mismatch, but the added disclosures exceed the annotation baseline.

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 first sentence is a marketing question ('Did your AI pick the right product?') rather than the operation, and 'Free for shoppers.' is promotional filler that does not help an agent invoke the tool. Em-dash-heavy framing and the third-person brand reference lengthen the text without adding invocation-relevant detail.

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?

An output schema exists, so return-shape explanation is not required, and annotations cover the safety profile. The description covers both input modes and the meaning of a positive verdict, but omits what a negative/partial result looks like and how the two input routes are prioritized — meaningful gaps for a verification tool with three undocumented parameters.

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 partly does: it explains that 'product' carries a name and size or a barcode, and that 'country' scopes the record lookup, plus the receipt_id alternative. But it leaves the concrete format of the single 'product' string ambiguous (how name, size and barcode are combined), and never mentions that country defaults to 'UK' or how receipt_id and product interact.

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 states a concrete verification function: 'shopfetch checks it is the real thing — same product, same size, same pack — against the record for your country.' A specific verb (checks) and resource (product record per country) are present. The rhetorical opening question and brand framing dilute it slightly, but an agent can still tell this is a product-authenticity verification tool.

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?

It names two input routes — 'the product your AI chose (its name and size, or its barcode) and your country' or 'the receipt on your order confirmation' — which implies the calling contexts. However, it never states when to prefer receipt_id over product/country, what to do when both are supplied, or any exclusion. Usage is implied rather than specified.

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