veto_prompt_optimizer

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

Annotations already convey readOnlyHint=true, indicating no side effects. The description adds valuable context: it uses a local agent loop, requires no API keys, and performs both scoring and rewriting. It does not contradict annotations and provides insight into the tool's behavior beyond the structured fields.

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 two sentences, front-loading the core function (scoring and rewriting) and adding a key differentiator (no API keys, local loop). Every sentence contributes meaning without redundancy, achieving high efficiency.

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 tool has no output schema, but the description hints at the return format ('rewritten version with improvements'). It covers the main inputs and outlines the analysis scope (failure modes). For a relatively simple tool, this is sufficiently complete, though a bit more detail on the output structure would help.

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 100%, so a baseline of 3 is appropriate. The description briefly mentions 'failure modes' but does not elaborate on parameter meaning beyond what the schema provides. The schema descriptions for 'goal', 'role', and 'prompt' are adequate, and the description adds marginal value.

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 scores prompts for specific failure modes (vague role, missing output format, injection-prone, no examples) and returns a rewritten version. The verb 'scores and returns' paired with the resource 'prompt' is specific and distinct from sibling tools, which target different tasks like accessibility or code review.

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 for prompt improvement and highlights 'Zero API keys needed — uses the local agent loop', suggesting it is for local optimization. However, it does not explicitly state when to use this tool over alternatives, nor does it provide exclusions or prerequisites, leaving room for ambiguity.

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