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

Beyond the annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false), the description adds valuable behavioral context: results are filtered by token role so an empty result means 'nothing you can see', not necessarily 'nothing exists'; it defaults to active alerts only; and it intentionally cannot resolve/dismiss alerts. No contradiction with annotations.

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 front-loaded with the core purpose, then defaults, then caveats in a 'Two things worth knowing' format. Every sentence earns its place; the length is justified by the useful behavioral nuances and no redundant filler is present.

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 listing tool with six parameters and no output schema, the description provides the essential context: the kind of alerts, the response element fields, permission-based filtering, and non-mutability. Minor gaps remain for `sinceDays` and `alertType` value semantics, but the overall picture is clear enough for reliable invocation.

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 covers only one of six parameters (17%), so the description carries some burden. It does clarify the default status behavior ('Defaults to active alerts only') and hints at the alert fields returned, but it leaves `limit`, `sinceDays`, and `alertType` semantics to the schema. Since two parameters have enums and are self-explanatory, the gap is moderate.

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 verb and resource: 'Lists the risk alerts this workspace raised for the project on its own', followed by concrete examples of alert types. This clearly separates it from sibling tools like get_project_structure, get_task, or get_task_stats because it is exclusively about computed risk alerts.

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?

It gives an explicit when-to-use signal: 'the fastest way to answer "how is this project doing" with evidence instead of impression.' It also provides a clear when-not: 'you cannot resolve or dismiss an alert through this connector — that stays with a person in the UI, on purpose.' No sibling alternative is named, but none of the siblings serve the alert role, so the guidance is still strong.

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