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

Annotations declare destructiveHint=true, idempotentHint=true and openWorldHint=true, but the description adds substantial context beyond them: a closed trade returns its terminal state, route=best may split fills into legs, contract_note appears on every non-Kalshi exit, selling is never membership-gated, and live/poly_intl calls are refused with live_not_hosted on this paper-only server. This is rich disclosure the structured fields do not carry.

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?

Purpose is front-loaded and every clause carries information, but the procedural tail is a dense run-on of sentence fragments ('Live=true sells on Kalshi. Pass one. Default is paper.') that is harder to parse than it needs to be. Size is defensible for a 15-parameter tool, but the telegraphic style costs readability.

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?

With an output schema present, return values needn't be explained, yet the description still names the fields an agent must surface (proceeds_dollars, pnl_dollars, fill_venue, price_cents, crosses_now). It covers venue selection, the paper-only refusal, the split-order case, and the confirm/idempotency dance — everything needed to call correctly.

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 description coverage is already 80%, so the schema carries most parameter documentation; some description content (confirm/idempotency_key requirements, time_in_force rest semantics) overlaps it. However, the description adds genuine semantics the schema lacks — what route=best vs route=kalshi means for fill venue, the relationship between the dry run's fill_venue and min_price_cents, and the 'pass one' rule for live/poly_intl.

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 opening sentence states a specific verb and resource — 'Exit an open position at the bid (current_bid_cents), or rest a limit exit' — and immediately distinguishes the two exit modes. It reads clearly against the buy-side sibling place_trade. An agent can tell what this does without opening the 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 explicit branching: with route=best, run dry_run=true first, report proceeds/pnl/fill_venue to the person, then re-call with confirm=true; otherwise pass route=kalshi. It also states when to pass min_price_cents based on the dry run's fill_venue, and that confirm plus a fresh idempotency_key are required except for dry_run. Alternative paths and their selecting conditions are named.

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