veto_decisions

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

The description adds significant behavioral context beyond annotations: it explains that constraints are persisted, can be disabled/enabled, the add action stores rules with forbidden_patterns, check action can read uncommitted git changes from project_dir, and forbidden_patterns are case-insensitive regexes with substring fallback. Annotations only indicate non-readonly and non-destructive, which the description aligns with.

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 three sentences plus a list of actions. It is front-loaded with the core purpose, includes a motivating example, and lists actions succinctly. No wasted words.

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?

The description covers the main workflow and relationships to sibling tools. It explains constraint scope, severity, and file_scope. However, it does not describe what the 'check' action returns (e.g., list of violations) or the output format. Given no output schema, this is a minor gap but the description still provides good context for a tool with 10 parameters.

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%, so baseline is 3. The description adds meaningful context by explaining the workflow: actions map to parameters (e.g., add requires rule and forbidden_patterns, check uses diff or project_dir). It provides a concrete example ('we use Postgres' with forbidden patterns ['mongoose', 'mongodb']), which helps understand parameter usage beyond schema descriptions.

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 that the tool records architectural decisions as machine-checkable constraints and flags diffs that violate them. It distinguishes from sibling tools by mentioning that veto_diff_review and veto_ci_gate automatically fail violations, clarifying the relationship.

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 a concrete scenario: AI assistants forgetting decisions across sessions, with an example of recording a Postgres decision. It explains how to use the tool for enforcement, and implicitly differentiates from siblings that perform the actual review/gating.

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