get_remediation_leverage

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

With no annotations provided, the description fully carries the behavioral disclosure burden. It explicitly states 'Read-only', which is critical for safety. It also discloses the output structure and the nuanced behavior for composed models (e.g., inherited controls owned by ancestor models, the inherited flag, and the summary count). This goes beyond the schema and provides valuable context about what the tool returns and how it behaves in different model types.

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 lengthy but well-structured: the first paragraph delivers the core purpose and usage, and the second handles composed model details. Every sentence adds value—the output fields, the read-only note, the owner_model details, and the summary. It is front-loaded with the most important information. While it could be trimmed slightly, the detail is warranted for the tool's complexity.

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 complexity and the presence of an output schema (as signaled), the description provides ample context: it explains the meaning of the key outputs (ranked, greedy_plan, summary), the composed model nuances, and the ownership implications. It also includes read-only status and usage intent. This level of completeness ensures an agent can use the tool correctly without needing additional documentation.

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 only 50%: model_id is described but server_version has no description. The tool description does not mention either parameter or add any semantics. It focuses entirely on output and usage, failing to compensate for the missing schema documentation. Given the low coverage, the description should have clarified at least the server_version parameter, but it does not.

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 the tool's function: 'Remediation-leverage plan for a model' and explains the output structure (ranked, greedy_plan, summary). It distinguishes itself from siblings by focusing on prioritization of implementation work, explicitly saying 'Use to prioritize implementation work' and contrasting with fixing objectives one at a time. This differentiates it from other control-related tools like get_controls or get_mitigation_groups.

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 clear usage context: 'Use to prioritize implementation work' and explains the benefit of a single call. It does not explicitly state when not to use it or mention alternative tools, but the use case is well-defined. The absence of exclusions and alternative references keeps it a step below exceptional, but the guidance is unmistakable.

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