Identify Unreliable Dataset Publishing

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it clarifies that reliability measures timeliness of successful freshness observations (not uptime), that sample days are included for evidence depth, that it reads precomputed data, and that DataPulse is read-only with rate limits (roughly one request per second with burst). This is rich behavioral disclosure. The only minor gap is not describing the exact output structure, but the output schema exists, so that's not required.

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 a single dense paragraph that front-loads the core purpose and ranking order, then adds usage exclusions, behavioral context, and rate-limit guidance. Every sentence earns its place, though the paragraph is long and could benefit from slight structural separation (e.g., a second sentence for rate limits). It is appropriately sized for the complexity and contains no filler.

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?

Given the tool's moderate complexity (2 optional params, output schema present, rich annotations), the description is complete. It covers what the tool returns, how results are ordered, what reliability means, when to use alternatives, how to interpret empty results, and operational constraints (rate limits). An agent has everything needed to select and invoke this tool correctly without opening the schema.

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 documents both parameters (limit and at_or_below_grade) with defaults, examples, and inclusive threshold semantics. The description adds the ranking context ('worst grades and lowest on-time percentages first') and the inclusive threshold meaning ('at or below'), which slightly enhances the schema. However, the schema already explains the inclusive behavior in the at_or_below_grade description, so the added value is marginal. Baseline 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 states a specific verb ('Return'), a specific resource ('datasets whose evaluated publish-reliability grade is at or below a threshold'), and a clear scope ('the unreliable ones'). It also distinguishes itself from siblings by naming find_anomalies, find_deteriorating, find_recovering, and find_schema_drift as alternatives for different concerns. This is a clear, specific purpose that an agent can act on.

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 explicitly says when to use it ('Use it for timeliness reliability grades') and when not to use it ('do not use it for individual anomalies, trends, or structural drift'), and names the exact sibling tools to use instead. It also clarifies that an empty result means no published grade meets the threshold, which is a key interpretation guideline. This is exemplary usage guidance.

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