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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds the return value ("The companion's state"), which matters because no output schema exists, but it does not say whether omitted hp/boxUses fields are preserved or cleared, or whether permissions are required.

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 action and followed by the return value; nothing is padded. It is efficient, though extremely terse given the nested-object schema.

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 five-parameter tool with nested objects and no output schema, the description covers the core mutation and the return shape, and the 80% schema coverage fills in the field-level detail. The main remaining gap, partial-update semantics, is minor against the structured data supplied.

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 80%, so parameter meaning is largely documented structurally, including the nested hp.temp/hp.current fields and the free-form boxUses map keyed by card id. The description adds nothing beyond naming those two concepts, which is the baseline when the schema already does the work.

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 specific verb and resource ("Set a companion's hit points") and names the secondary effect (card uses spent). It is clear on its own, but it does not distinguish itself from the close sibling update_companion or explain what 'state' means versus a general companion update.

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 no guidance on when to use this instead of update_companion, update_character_state, or change_participant_health, nor any stated prerequisites such as needing to own or control the companion. The agent must infer usage purely from the name.

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