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

Annotations already declare readOnly, idempotent, closed-world, non-destructive behavior, so the safety profile is covered. The description usefully adds that results are ordered by strength and annotated with the shared traits, and that pair mode returns magnitude plus rationale. It says nothing about ambiguity in card names, unknown cards, or the API-key-limited result cap beyond what the schema states.

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 short sentences, front-loaded with the default behavior and then the opt-in variant. Every clause carries information about either output content or mode selection; nothing is filler.

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?

There is no output schema, so the description must sketch the return value, and it does for both modes (ranked synergies with shared traits; pair verdict with strength and reason). The default limit of 10 and the unauthenticated cap of 10 live in the schema, so the only real gap is undocumented behavior on unresolved card names.

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%, so the baseline would be 3, but the description adds meaning the schema does not: `with` is not a filter but a mode switch that converts the tool into a pairwise judgment returning strength and reasoning. It leaves `limit` and the oracle-id alternative for `card` entirely to the schema.

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 clearly conveys the resource (synergies for a card, ranked, with the shared traits that justify each pairing) and adds a second mode for judging a specific pair. It is specific rather than tautological, but it is written as a noun phrase with no explicit verb and does not contrast itself with siblings such as card_lookup or suggest_cards.

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 gives explicit conditional routing between its own two modes: omit `with` for a ranked list, supply `with` to ask whether two cards work together, how strongly, and why. What is missing is guidance relative to alternatives (e.g., when a plain card_lookup would be the better first step), so it stops short of a 5.

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