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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds one genuinely useful behavioral fact -- missing answers fall back to defaults -- but says nothing about how answers must be keyed, what happens with unrecognized question keys, or whether results vary with prior state beyond idempotency.

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 purpose is front-loaded, which is good, but the entire clinic enum is re-listed inline, largely duplicating structured schema data. The parenthetical labels justify some of that bulk, yet the result reads as a single sprawling sentence that an agent must parse rather than a tight, scannable definition.

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?

With an output schema present, the description needn't explain return values, and annotations cover safety, so the remaining burden is input behavior. Default handling is disclosed and the clinic catalog is complete. The one meaningful hole is the key format for the answers object, which is not covered anywhere.

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 carries the burden. The clinic enum values are largely self-describing and the labels add a small amount of gloss, but the free-form 'answers' object is left completely opaque: neither schema nor description states that keys should be question identifiers obtained from list_clinics. That gap leaves the second parameter under-specified.

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 outcome (a personal answer with reasons and next steps) and enumerates all twelve clinics with human-readable labels, so an agent knows exactly what each call produces. It also distinguishes itself from list_clinics by routing discovery there. It stops short of a crisp verb+resource framing -- 'get a personal answer' is softer than naming the operation -- but the clinic catalog removes most ambiguity.

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?

There is real usage guidance: 'call list_clinics to see questions' tells the agent how to discover valid inputs, and 'Unanswered questions use defaults' sets expectations for partial input. However, it gives no guidance on when to pick run_clinic versus overlapping siblings such as compare_tax_regimes, check_gst_registration, or calculate_gst, even though clinic names like 'old-vs-new-tax-regime' collide directly with them.

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