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

With no annotations, the description carries the full burden and does so: it discloses the cost model (1 CRD per call, charged even on rejection, free on 429), the idempotency replay semantics including the 409 IDEMPOTENCY_KEY_REUSED case, the non-idempotent default, and the concrete error codes 400/404. This is exactly the behavioral context an agent needs before a mutating, billable call.

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 core action and the follow-up tools, then layered with idempotency, errors, and cost. Every sentence carries information, though the density of error codes and pricing in one paragraph makes it slightly harder to scan than a bulleted structure would be.

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 12-parameter, billable mutation with no output schema and no annotations, the description covers the return value (hold_id, status, idempotent_replay), the lifecycle, failure modes, and cost. Nothing an agent needs to call this correctly 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 83%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains what a replay of idempotency_key returns, that expires_at governs when funds can be released back, and that reference_id is filterable in list_escrow_holds. It does not explain user_id vs user_email precedence or metadata, leaving a small 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?

Opens with a specific verb and resource ('Reserve credits: deducts amount from an existing user and parks it in a hold') and immediately names the terminal siblings capture_escrow_hold and release_escrow_hold, so the agent can place this tool in the escrow lifecycle without opening any schema.

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 states the follow-up path ('Finish with capture_escrow_hold or release_escrow_hold'), the expiry escape hatch, and the exact condition for supplying idempotency_key ('anything an agent might retry') versus the consequence of omitting it. It also scopes x402_payment to a specific prior failure mode, which is genuine when-to-use guidance.

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