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

Annotations already declare a read-only, idempotent, non-destructive, closed-world call, so the safety profile is covered. The description nevertheless adds real operational detail: top-3 output shape (cards with sarcastic tagline, why-it-works, Dr. Waggs' reality check, breed link), the 'share the links' obligation, and the defaulting rule for non-key answers. It does not state cost/rate behavior or whether results are stable across identical inputs, but there are no annotation contradictions.

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?

Front-loaded with the trigger and the engine, then flows into output, prerequisites and exclusions. There is mild redundancy — '121 breeds' and the 'use when someone asks which dog breed suits them' clause restate the opening sentence — but the remaining sentences each carry distinct instructions (defaults, links, widget behavior, refusals).

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 10-parameter quiz tool with no output schema, the definition covers trigger, required-vs-default inputs, user-elicitation rules, result shape, link-sharing, widget-mode guidance and out-of-scope refusals. An agent has everything needed to call it and to render its answer correctly.

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% with enums fully described, so the schema carries the baseline. The description adds meaning the schema cannot: it designates living_situation, activity_level, experience, kids and alone_time as the five must-collect answers and states that all remaining parameters default to neutral, which tells the agent which fields it is expected to elicit from the user.

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 concrete verb and resource ('scores all 121 breeds with TheDogs.app's matching engine ... returns the top 3 matches as cards') and defines the trigger ('when the user wants a personal recommendation of which dog breed suits their home, schedule, activity level, experience or family'). It differentiates from the medical/training domain but never names the near-identical sibling assess_breed_fit, so the boundary against same-family tools is left implicit.

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?

Explicit when-to-use, explicit when-not-to-use ('Do not use for symptoms, emergencies or treatment'), and a hard prerequisite: the five key answers must come from the user, never guessed, with a stated fallback (ask in one short message, reuse earlier answers). It also tells the agent how to behave differently when a widget renders the results.

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