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

Annotations already indicate readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the agent knows it's a safe, non-destructive read. The description adds a key constraint: the topic must be one of the watched topics, which is useful context beyond the schema. However, it doesn't elaborate on pagination, ordering, or timezone handling, which could be relevant for time-series data. With annotations covering the safety profile, a 3 is appropriate.

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?

The description is concise: three sentences with no fluff. It front-loads the core purpose, provides a usage example, and ends with a prerequisite. Every sentence carries essential information, making it efficient for an agent to parse.

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?

The description is sufficient for an agent to select and call the tool correctly. It explains what the tool does, when to use it (with examples), and the prerequisite. The output schema is absent, but the tool returns a time-series of alerts, and the description implies the output is a chartable history. Given the simplicity of the tool (3 params, no nested objects) and annotations covering behavioral traits, nothing essential is missing.

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 100%, so parameters 'topic', 'hours', and 'limit' are fully documented in the schema with descriptions and constraints. The main description reinforces the 'topic' parameter by tying it to the watchlist, but adds minimal new semantic detail. Baseline 3 is appropriate since the schema does the heavy lifting; the description adds slight context on topic format (lowercase, matches arb_watchlist), which is already in schema description.

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?

Clearly states the tool's purpose: 'Spread history for ONE watched topic — the time-series of every alert that fired for that topic over the past N hours.' It specifies the exact resource (one watched topic) and the operation (retrieve time-series of alerts). Distinguishes itself from siblings like arb_recent_alerts ('recent alerts') and arb_watchlist ('enumerate watched topics') by focusing on historical spread for a single topic.

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?

Provides clear usage context: 'Use to chart how a specific cross-venue mispricing evolved (e.g., ...)'. Also gives an explicit prerequisite: 'Topic must be one of the watched topics — call arb_watchlist to enumerate.' This tells the agent when to use this tool and what to do first, effectively differentiating it from alternatives.

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