edit_attacker

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

With no annotations, the description carries full burden. It discloses that likelihood is server-derived, that factor edits require change_reason for audit trail, and that identity-bearing edits are LLM-gated. Error conditions are also specified. This is transparent and informative.

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 very concise, using only a few sentences to convey purpose, key constraints, and errors. It is well-structured with clear sections. Every sentence adds value, and no unnecessary information 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 the complexity (15 parameters, 3 required, output schema exists), the description covers essential aspects: main function, partial update behavior, likelihood derivation, gating, attestation purpose, and error conditions. It does not need to repeat output schema details. Minor gaps could include more detail on attest_position relationship with trust_boundary_ids, but overall complete.

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 93%, so baseline is 3. The description adds value beyond schema by explaining that likelihood is derived from factor fields and that change_reason is required when factor fields are provided. It also explains the purpose of attest_position. This extra context justifies a higher score.

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 'Edit an existing attacker. Only provided fields changed.' This explicitly identifies the verb (edit) and resource (attacker), distinguishing it from sibling tools like add_attacker, remove_attacker, and restore_attacker.

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 context on when to use certain fields: mentions LLM-gating for identity-bearing fields (capability, archetype, position) and that factor and trust_boundary edits skip the gate. It also lists error conditions (503, 502, 400). However, it does not explicitly compare to alternatives or state when not to use this tool.

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