delimit_security_deliberate

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

No annotations are provided, so the description carries full burden. It states 'runs deliberation' but does not disclose whether the tool modifies state (e.g., writes to ledger), requires certain permissions, or has rate limits. The behavioral impact on security findings is not clearly communicated.

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?

Two sentences plus a concise list of classification outcomes. Front-loaded with verb and domain. No redundant words, but the list could be more integrated into prose. Overall efficient.

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 output schema and 100% parameter coverage, the description adds the classification categories. However, it omits whether the tool is read-only or mutates state, which is important for a security triage tool. Adequate but leaves behavioral ambiguity.

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 100%, baseline is 3. The description adds context that the 'findings' parameter can be empty for auto-mode, and mentions the focus parameter implicitly via the classification. It does not elaborate on the 'repo' parameter. Value added is minimal beyond 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 the tool performs triage of security findings with four specific classifications. It mentions source options (ledger or JSON string). However, it does not explicitly distinguish itself from sibling tools like delimit_security_scan or delimit_deliberate, making the purpose clear but not uniquely differentiated.

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 implies usage when security findings need classification, and specifies two data sources ('from the ledger (auto)' or 'from a JSON string'). It lacks explicit guidance on when not to use this tool or alternatives, such as for just scanning vs. in-depth deliberation.

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