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

Annotations only declare readOnlyHint=true, but the description adds substantial beyond-schema behavior: the 24-hour terminal-order window, inclusion of imported broker-account orders, pagination via nextToken, attribution requirements (matching order_id events and revision/run timing), and conflict resolution rules against get_deployment_position_telemetry avg_fill_price. These are real operational caveats an agent could not infer from the annotation.

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?

Roughly 400 words with poor front-loading: the opening sentence is about saved-code repairs not requiring live orders, which does not describe this tool at all. Large portions read as workflow/policy instructions for the calling agent rather than tool documentation. Useful content exists but is not structured for scanning; the return-format and filtering guidance should come first.

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 13-parameter, no-output-schema tool, the description is complete enough to call correctly: return fields are enumerated (timestamp, symbol, action, quantity/filled quantity, fill price, order_id, status, reason, option metadata), pagination is described, and attribution caveats are covered. Minor shortfall is the imprecise mapping of the four time-window parameters and the status-vs-statuses relationship.

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?

With 0% schema description coverage across 13 parameters, the description carries the burden and largely meets it: it documents status (with example 'filled,canceled'), statuses, case-insensitive symbol, hoursAgo, includeOpen, time window via ISO-8601 or Unix epoch, default sort=desc, limit sizing guidance, and nextToken pagination. Gaps remain: it never clarifies the distinction or precedence between status and statuses, or maps the prose 'time window' cleanly onto the four separate start/end ISO/epoch fields.

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 core purpose is stated precisely: 'Returns orders tracked for a live bot: active/open orders plus recent terminal orders (filled, partially_filled, canceled, rejected, expired) updated in the last 24 hours.' It also explicitly distinguishes itself from show_bot_activity and get_deployment_position_telemetry. However, the actual purpose statement is buried mid-paragraph behind workflow policy text, so an agent must read past several sentences before learning what the tool does.

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?

This is the description's strongest quality. It names alternatives and the conditions selecting them: 'For current bot performance and decision summaries, use show_bot_activity first,' 'Use this separate reader for a targeted order/fill investigation requiring its filters, not to repeat that report,' and 'For live order analysis, use includeOpen=true, sort=desc, a small limit, and status/statuses filters.' It also states when NOT to use placeholders or invented IDs. Routing is explicit and actionable.

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