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

Annotations already cover read-only (readOnlyHint=true), idempotent (idempotentHint=true), and non-destructive (destructiveHint=false). The description adds behavioral context beyond annotations: it specifies that alerts are 'active', describes returned fields (header, effect type, cause, severity), provides severity thresholds (7+ moderate, 9-10 major), and notes real-time data with no upstream cost. This exceeds the baseline and provides useful operational detail.

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 well-structured and front-loaded with the core purpose. It lists disruption types, return fields, filters, severity thresholds, and licensing in a logical flow. While slightly longer than the minimal example, each sentence contributes value and avoids unnecessary redundancy with the schema. It is concise enough for an agent to parse quickly.

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 presence of an output schema und the rich set of annotations, the description covers all necessary aspects: purpose, return fields, filter options with concrete examples, severity interpretation, and licensing/cost. Since output schema describes return structure, the description does not need to elaborate further. It is complete for an agent to select and invoke the tool 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 baseline is 3. The description mentions filters and provides examples (e.g., route ID 'Red', stop ID 'place-sstat') and restates severity interpretations, but these largely mirror the schema descriptions. It does not add significant new semantic detail beyond what the schema already documents, so it stays at the baseline.

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 'Get active Boston MBTA service disruption alerts' followed by specific disruption types (delays, cancellations, detours, shuttle buses, station closures, elevator/escalator outages). It clearly distinguishes from sibling tools like mbta.transit.predictions or mbta.transit.routes by focusing on alerts. The verb 'Get' is specific and the resource is well-defined.

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 implies usage when the user needs service disruption alerts by describing the operation and filters. It does not explicitly name alternative tools or provide when-not-to-use guidance, which is a common shortfall. While it lists filtering options (route, stop, severity, lifecycle, effect), it lacks explicit comparison to siblings like mbta.transit.stops or predictions.

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