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

Annotations only declare the basic safety profile (not read-only, open world, not idempotent, not destructive). The description goes beyond that with outcome mechanics: feeding timing windows change trust/health, and reflect notes are publicly visible on the pet page, /reflections and other agents' results. Response shape and cooldown behavior remain undocumented, keeping it from a 5.

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 endpoint and the action list, then layered with the highest-value constraints. Five sentences, each carrying a distinct rule, though the creature_id alias requirement restates what the schema already documents.

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 non-idempotent mutation tool with no output schema, the description covers target selection, action enumeration, action-specific constraints and a public-visibility side effect, which is close to sufficient. It omits any mention of failure modes, preconditions such as species preferences, or what a successful call returns.

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 is 3; the description still adds meaning by explaining that action choice has state-dependent semantics (feeding timing, reflect-only while asleep) and that id/creature_id are interchangeable aliases under a specific condition. It repeats the schema's creature_id rule, but the action semantics are genuinely new.

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+resource (care actions on a creature) and enumerates the exact seven actions, with the underlying endpoint for traceability. It is clearly distinguishable from siblings like get_creature_status or get_care_history, which read state rather than mutate it.

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?

Gives real conditional guidance: multi-creature calls must pass creature_id or id, and sleeping creatures only accept reflect. It stops short of routing to alternatives (e.g., calling get_creature_preferences before feeding), which is only implied by the schema, not the description.

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