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

The description says 'Idempotent on batch_id', but the annotations declare idempotentHint=false, which is a direct conflict on the one behavioral trait an agent uses to decide whether retrying is safe. Beyond that conflict, the description does disclose genuinely useful behavior (hash-chained, never disbursed twice, only newly-accrued proceeds for verified projects), but the idempotency contradiction undermines the reliability of the whole behavioral statement.

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?

Three dense sentences, each doing work: creation semantics first, then the idempotency and scoping rules, then the downstream use. The parenthetical '(content-addressed, hash-chained)' is compact and informative; no filler.

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 one-parameter mutation tool with an output schema, the description supplies the needed effects and constraints: what gets frozen, which proceeds qualify, and no double disbursement. The main gap is that it gives no permission or prerequisite information and contradicts the idempotency annotation, which an agent must resolve before calling.

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?

There is a single parameter and schema description coverage is 0%, so the description carries the burden. 'Idempotent on batch_id' is the only added meaning: it tells the agent that batch_id is the deduplication key. It never says where batch_id comes from, what format it takes, or whether it must be pre-registered by disbursement_schedule.

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: 'Freeze the current disbursement schedule into a certified, tamper-evident batch (content-addressed, hash-chained)'. That is clearly distinct from siblings like verify_disbursement, verify_certificate and settlement_batch, which verify or settle rather than certify.

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 closing sentence gives a clear decision context: this produces the record that the CEO executes actual Stripe transfers against, so an agent knows to call it before real money moves. It never explicitly excludes alternatives or names verify_disbursement/settlement_batch as the thing to use instead, so routing is implied rather than spelled out.

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