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

The description adds meaningful behavioral context beyond the annotations: reliability is defined as timeliness of successful freshness observations rather than uptime, results are sorted by worst grades and lowest on-time percentages first, and sample days are included to help agents assess evidence depth. This gives the agent a clear model of what the tool returns and how to interpret it.

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 no filler. The core behavior and ordering are front-loaded, and the clarifying note about reliability versus uptime earns its place by preventing a common misinterpretation.

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 read-only tool with two optional parameters, a full output schema, and strong annotations, this description is complete. It explains what is returned, how results are ordered, how reliability is measured, and why sample days appear, leaving no critical gap for an agent to call it 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 100%, so the schema already fully documents both parameters, including defaults, ranges, and examples. The description adds some interpretive context around the threshold and ordering, but it does not materially expand on parameters beyond what the schema provides. The baseline of 3 is appropriate.

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 clearly identifies the verb, resource, and selection criterion: return datasets with a publish-reliability grade at or below a threshold. It also explains the ordering, which helps distinguish this from generic lookups. However, it does not explicitly distinguish itself from closely related sibling tools like find_stale or find_deteriorating.

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 context implies this tool is for finding unreliable datasets by grade, and clarifies that reliability is about timeliness, not uptime. It does not explicitly state when to prefer this over find_stale or other sibling tools, nor does it mention exclusions. Guidance is therefore implied rather than explicit.

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