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

Annotations already supply the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=true), so the description only needs to add context. It does add account scoping and recency ('the account's recent'), but says nothing about ordering, how many runs are returned by default, or rate-limit/behavioral constraints.

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?

It is one short fragment with no filler, but it is under-specified rather than genuinely concise — an incomplete noun phrase that omits the action verb and any routing context. Brevity here reflects a gap, not discipline.

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?

No output schema exists, so the description should at least indicate what a 'run' record contains or how results are ordered; it does neither. For a list tool in a crowded deep_*/autopilot_* sibling set, the definition is too thin to call correctly without guessing.

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 100% and the single 'limit' parameter is fully documented in the schema (min 1, max 50, default 20). The description adds no syntax or semantics beyond what the schema already provides, so the baseline 3 applies.

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 fragment 'The account's recent deep research runs' identifies the resource and the account-scoped, recency-limited view, but contains no verb and does not distinguish this from siblings like get_deep_analysis, get_deep_thread, or deep_events. It largely restates the title rather than sharpening the purpose.

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?

No when-to-use guidance, no mention of alternatives such as get_deep_analysis for a single run or get_deep_thread for thread detail. The agent must infer that this is the discovery entry point for the other deep_* tools.

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