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

With no annotations, the description carries the full burden and does substantial work: it discloses the authoritative source (manufacturer's UK leaflet), the return content ('what it means and what to do'), and an escalation rule ('when to stop and call the pharmacist'). It stops short of stating that the call is read-only/no-side-effect or noting any coverage limits (e.g. non-UK pens, non-listed symptoms).

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?

A single dense sentence with the purpose front-loaded and the symptom enumeration in a parenthetical, so nothing is wasted. The embedded list makes it slightly hard to scan, but every clause adds information.

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-enum lookup tool with no output schema, the definition supplies purpose, source, return content, and the safety escalation threshold. The only omission ('last-dose') is minor against a schema that already constrains both parameters to closed enums.

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 0%, so the description must compensate; it partly does by glossing the symptom enum in plain language ('won't dial, no clicks, stuck, not at zero, no drop at the needle, a bubble, a leak, cold, unsure'). But the enum value 'last-dose' is never mentioned or explained, and the 'pen' parameter values are left entirely to the enum with no note on scope (e.g. UK-available devices only).

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 ('Answer a GLP-1 pen problem ... for a given pen') and enumerates the concrete failure modes it covers, plus the source ('maker's UK leaflet') and the shape of the answer. It is clearly distinguishable from data tools like bmi_check, though it never names its closest sibling pen_howto, leaving the boundary to inference.

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?

The symptom list implicitly defines when to call it (dial/click/dose/drop/bubble/leak/cold/unsure problems), which is real usage guidance. However, there is no explicit exclusion or routing: nothing says to use pen_howto for normal operation instructions, or storage_check for the 'cold' case that overlaps that sibling. The agent must infer the split.

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