add_attacker

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

The description discloses that the tool creates a new version, that the backend LLM reasons factor decomposition, and details three possible outcomes (normal create, auto-restore, similar-rejection) with specific error codes (503, 502). This goes well beyond the absent 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 concise and well-structured: purpose statement, usage details, and outcomes/errors. Every sentence adds value without redundancy.

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 presence of an output schema, high schema coverage, and no annotations, the description covers purpose, usage, behavioral traits, error handling, and cross-references to sibling tools ('add_asset', 'edit_attacker'). It is complete for the tool's complexity.

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 coverage is 83% (high), so baseline is 3. The description adds value by explaining that fields like capability, position, archetype, trust_boundary_ids are 'identity-bearing' and that factors are auto-reasoned, which is not in the schema. Also mentions override via edit_attacker.

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 adds an attacker to a threat model and creates a new version. It distinguishes itself by referencing 'Mirror of add_asset semantics' and mentions the sibling 'edit_attacker' for post-create modifications.

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 explains when to use this tool (supplying identity-bearing fields) and directs post-create modifications to 'edit_attacker'. It also describes three outcomes and error codes. However, it lacks explicit 'when not to use' guidance.

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