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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals that the tool returns a JSON string, and it explains pagination, search, sort, and the fallback to global tenant when project_key is omitted. However, it does not explicitly state whether the operation is read-only (though 'list' implies it), nor does it mention permissions or potential side effects, which would be valuable given no 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 well-structured as a docstring with a one-sentence summary, an args list, and a returns line. It is front-loaded with the main purpose and each parameter line is concise and informative. No fluff or redundant content 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?

Given that the output schema exists, the description does not need to detail the return structure. It covers all parameters and the high-level return type. It omits potential error conditions and auth requirements, but for a listing tool with all optional parameters, the description is fairly complete and provides enough context for an agent to invoke 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?

The schema has 0% description coverage, so the description compensates by explaining all six parameters with their defaults and meanings. This adds value beyond the schema's bare titles. The explanations are mostly clear, though some are terse (e.g., 'Search filter', 'Sort order' for sort_descending), but they are sufficient for basic usage.

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 states 'List all roles for a project' with a specific verb (list) and resource (roles). It distinguishes itself from siblings like create_role and get_role_permissions by focusing on the listing operation at the project level. The purpose is unambiguous and immediately understood.

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 provides contextual details such as project scoping and parameter defaults, but it does not explicitly mention when to use this tool versus alternatives like list_permissions or get_role_permissions. The appropriate usage is implied by the name and description, but no clear 'when' or 'when not' guidance is given.

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