add_mitigation

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

With no annotations, the description carries the behavioral disclosure burden. It discloses that this is a mutation operation, supports batch operations, and returns a confirmation message with IDs. However, it includes a 'ctx' parameter in the args list that is not present in the schema, and it claims 'content' is required for single item mode while the schema marks it optional with a null default. These inconsistencies muddy the behavioral expectations.

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 structured with an intro, usage instructions, arg list, and return value, but it contains redundancy: 'Add a new mitigation to the model' is repeated in the first line and second paragraph. The inclusion of 'ctx' in the Args list, which is not part of the input schema, adds unnecessary clutter. Overall it is readable but not as tight as it could be.

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 tool with 8 parameters and batch capabilities, the description provides the basic usage and return value but lacks details on the schema of items in batch mode, potential validation rules, and error handling. It doesn't explicitly mention whether mitigations must be linked to threats or if any prerequisites exist. Given the lack of annotations and output schema, a more complete description would be expected.

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 has 0% description coverage, so the description must compensate. It lists all 8 parameters with brief explanations, including the crucial 'items' parameter for batch operations. It also adds constraints like 'content is required for single item mode'. Though some descriptions are vague (e.g., 'Type of the mitigation'), the description provides meaningful semantics beyond the bare schema.

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 it 'Adds one or more mitigations to the threat model' using a specific verb and resource. It distinguishes itself from sibling tools like update_mitigation and delete_mitigation by focusing on the creation aspect and explicitly mentioning batch support.

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 explicit guidance on when to use single item vs batch mode: 'For single item: provide content and optional fields directly. For batch: provide a list of mitigation dicts in the items parameter.' This is clear usage context, though it doesn't explicitly mention alternatives or when not to use the tool.

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