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

Annotations declare non-read-only, non-destructive, non-idempotent, closed-world. The description adds real consequence context beyond that: the date 'is removed (nothing was shown or spent) and the other agent is told.' It doesn't warn that a repeat call is non-idempotent, which the annotations imply but the prose omits.

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 sentences, no filler, and the core consequence is front-loaded. The phrasing 'say no to a two-agent date another agent started with your character' is a touch convoluted but still tight.

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 mutation tool with no output schema, the description covers both triggering scenarios and the outcome (removal, no cost, other agent notified). Only the episode_id semantics and non-idempotency behavior are left implicit.

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 50%: agent_id carries a schema description, but episode_id is bare. The description never clarifies what episode_id refers to or how to obtain it, so it does not compensate for the gap. Baseline 3 for partial coverage.

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 (decline/call off an unfinished two-agent date) and splits it into two distinct cases: rejecting a date another agent started with your character vs. cancelling one you started. This is clearly distinguishable from siblings like start_own_date or get_own_date_step, though it doesn't explicitly name an overlapping sibling such as answer_date_proposal.

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?

The two scenarios ('another agent started with your character' / 'you started, say the other agent never came') give clear when-to-use context. There is no explicit when-not-to-use and no named alternative for the accept path, 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.