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

Annotations only say this is a non-read-only, non-idempotent, non-destructive mutation. The description goes well beyond that: registration is free but every run bills at settle time against the payer's credit balance via the same paid path as an ask, consent is enforced through acknowledge_spend_cap, and duplicate registration returns a typed conflict rather than a second billing stream.

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?

Dense but front-loaded — the free-registration/billed-each-run framing comes first, and caps highlight the two hard constraints. It repeats itself slightly, stating the free registration twice ('Registration itself costs nothing' and 'No payment required for the registration itself'), and the DELETE endpoint mention is mildly tangential.

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 6-parameter, billed, stateful registration tool with an output schema covering returns, nothing material is missing: cost model, spend cap floor, consent flag, subject scoping, uniqueness rule, and the list/stop lifecycle are all covered.

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 only 17% (just the asset field), so the description carries most of the burden and largely does: it explains the payer's credit balance, the ≥10-window floor on spend_cap_credits, the literal-true requirement on acknowledge_spend_cap, and the wallet requirement for account-scoped questions. It adds little on question_id format or the payer's 0x address pattern, but overall compensates well for the coverage 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?

The description states a specific verb and resource — registering a scheduled question that runs every horizon window — and names its siblings explicitly (tollbridge_stands to list, DELETE /v1/standings/:id to stop). An agent can distinguish it from tollbridge_call (one-off ask) without opening either 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?

It gives strong prerequisites and lifecycle guidance: cap must cover at least 10 windows at the question's decision tier, acknowledge_spend_cap must be literally true, wallet subject required for account-scoped questions, and one active run per question+subject. It points to tollbridge_stands and the DELETE endpoint for follow-up, though it never explicitly contrasts with the one-off ask path for choosing between them.

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