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

Annotations already declare readOnlyHint=true, and the description reinforces it with 'Read-only.' The description adds behavioral context by specifying the time window options (1h/24h/7d/30d) and the type of data returned (every declared step, failure step, page). This adds value beyond the schema and annotation without contradicting them. No hidden side effects are mentioned, but the bar is met given 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?

The description is two sentences, with the first packing all essential facts about the resource, data, and scope, and the second giving a practical use case. There is no redundant or filler language; every phrase contributes.

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, the description need not detail return formats. It explains what the tool returns conceptually, the windows, the monitor type, and a motivating use case. For a two-parameter read-only tool, this is complete.

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?

The input schema already provides descriptions for both parameters with 100% coverage. The description only restates the window choices and confirms the id must be a flow monitor (already in the schema). No additional parameter semantics are added, so the baseline of 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 description opens with a specific noun phrase ('A browser flow monitor's recent runs') and details the contents (steps, outcomes, durations, failure step, page). It clearly specifies the resource (flow monitor runs) and the action (get). It also distinguishes from siblings by focusing on recent runs with failure details, and even offers a concrete use case ('why a login check failed').

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?

The description provides a clear context for when to use the tool: 'Use this to answer why a login check failed.' It implies this is the diagnostic tool for inspecting individual runs and step outcomes. However, it does not name alternative tools or specify exclusions, so it falls short of full alternative guidance.

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