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

Annotations already declare readOnlyHint/idempotent/closed-world, so "Read-only" is mild restatement, but the description adds substantive behavioral detail the annotations lack: the exact field inventory returned, including derived scores and child counts. It omits pagination, ordering, and behavior when a project has no legacy systems.

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?

Front-loaded with the action and scope, then the field list, then the routing hint. The parenthetical enumeration is dense but earns its space because there is no output schema; the redundant "Read-only" is the only wasted token.

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 no output schema, spelling out returned fields is exactly the right compensation, and the safety profile is covered by annotations. Remaining gaps are minor: no indication of result volume, ordering, or empty-state behavior.

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?

A single parameter with 100% schema coverage, so the schema already explains projectId as a UUID. The description adds no further meaning (e.g., whether the UUID must be a Modernize-enabled project or how invalid IDs behave), so baseline 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?

Names a specific verb (List) and resource (legacy systems) scoped to a project, and enumerates exactly what each entry contains (name, status, type, language, scores, child counts). It is clearly distinguishable from the sibling stride.get_legacy_system, which is called out as the single-system alternative.

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?

Explicitly routes the agent: use get_legacy_system when the full context bundle is needed. Together with the scoping keyword "in a project" this gives clear conditions for use, though it doesn't say when this listing should be preferred over other survey tools such as list_processes or list_projects.

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