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

Goes far beyond the annotations by disclosing the full economic consequence chain: funds stay held, the supplier may refund or contest, silence for 72 hours auto-refunds, a contested objection is ruled by Licium within 7 days, and no ruling means refund. It also names the emitted notice (capability_call.dispute_resolved), who receives it, and how refunds are routed (x402 to the key balance, referral credit back to credit) — none of which appears in structured fields.

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 action and its precondition, and every clause carries real information — refund timing, notice, quota, key precedence. The middle section is a dense semicolon-chained run-on covering resolution mechanics that an agent mostly needs only after calling, so it is slightly over-full for a calling decision.

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?

No output schema exists, yet the description still explains what the agent can expect afterward (a dispute_resolved notice, and reading the outcome via capability_call_get) plus refund routing and the timeout rulings. For a stateful financial mutation this is essentially complete for correct invocation.

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 0%, so the description must carry the burden; it does well on the ambiguous parts, explaining the agent_key vs api_key precedence and characterizing 'reason' as 'saying what is wrong'. The 'call_id' parameter is only implicit ('a part result') and its UUID format/where to source it is left to the schema, which is a small remaining gap.

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 ('Object to a part result') and pins down the exact precondition state: the result must be 'in_review' and the objection must land 'before its review_ends_at'. It also implicitly separates the buyer's action from the supplier's by describing the counterparty as the one who 'refunds you or contests it', so an agent knows which side of capability_call_dispute_respond it is on.

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 a concrete trigger (a result in review that is wrong), an explicit exclusion (must be before review_ends_at), a hard quota ('at most 3 open objections at once'), and a routing rule for ambiguous credentials ('with both agent_key and api_key, the key that made the call is used'). It also points to capability_call_get for reading the outcome, which is the correct sibling for the follow-up read.

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