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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real context: deprecated status, sunset date, credit cost tier, and that the cast is unseeded random rather than reproducible. The only weak spot is the ambiguous 'input ignored' claim, which sits oddly beside two documented request parameters.

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 critical information — deprecation and replacement — is in the first sentence, and the metadata block is scannable. It is somewhat repetitive, stating DEPRECATED in the title, the first sentence, and again in a trailing warning line, which costs it a point.

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 deprecated two-parameter tool with an output schema, everything an agent needs is present: why to avoid it, what to use instead, how long it remains callable, and its cost. Return values are covered by the output schema, so nothing material is missing.

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 both `fields` and `precision` are fully documented in the schema and the description need not restate them. 'Input ignored' adds a small amount of meaning (output is not driven by request input) but does not clarify how those two parameters interact with the cast, so the baseline 3 applies.

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 ('Casts a single I Ching hexagram') and explicitly marks itself as the legacy un-namespaced variant, so an agent can distinguish it from the six /iching/* siblings without opening any schema. The deprecation is front-loaded in the title and repeated in the body.

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?

Explicitly says to avoid it and names the replacement set, singling out `/iching/throw-coins` as 'seeded + reproducible' so the agent knows why it is preferred. It also gives a hard operational cutoff ('Still works until its 2027-06-16 sunset, then removed'), which is exactly the when-not-to-use detail an agent needs.

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