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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: it returns a page rather than data, and it explicitly forbids soliciting order numbers or email addresses because the destination page handles verification. That interaction policy is exactly the kind of context annotations cannot convey.

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?

Two sentences, both front-loaded: the topic enumeration first, the behavioral constraint second. No filler, no repetition of the title, and the most operationally important rule (never ask for order numbers) is placed last for emphasis without bloat.

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 single-enum-parameter, no-output-schema router tool, the description covers purpose, all topic values, return shape ('the right Padel USA page'), and the PII handling rule. Only the exact return form (URL vs. text vs. link object) is left vague, which is a minor gap for a tool this simple.

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 carry the meaning of the single 'topic' parameter — and it does, spelling out all five enum values in natural language ('start a return or exchange' = returns, 'report a lost or damaged parcel' = shipping_problem, 'contact the team' = contact). The mapping is slightly loose for shipping_problem versus warranty, but an agent can resolve it from the prose.

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 names the resource (Padel USA post-purchase help pages) and enumerates the concrete topics: tracking, returns/exchanges, warranty claims, lost or damaged parcels, contact. The phrase 'After a purchase' cleanly separates it from the pre-purchase siblings (find_racket, search_products, racket_quiz), though it does not name any sibling explicitly. The verb is soft ('where to track... Returns the right page') but the outcome is unambiguous.

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 opening 'After a purchase:' sets a clear usage context, and each listed scenario maps to a reason to call it. It does not state exclusions (e.g., what to do for pre-purchase questions or cart issues, which the sibling tools handle), so the agent must infer the boundary. Still, the post-purchase framing is strong enough to route correctly.

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