Veto — SQL Safety & Cost Oracle

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

With no annotations, the description discloses that the tool returns a verdict with findings, that schema enables cost analysis on a throwaway Postgres, and that no separate tool is needed. It implies read-only behavior but could be more explicit about non-destructive nature.

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 with no wasted words. First sentence states the core purpose; second explains the key optional parameter and its benefit. Front-loaded and 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?

The description covers the two modes of operation (static vs cost analysis), explains the optional schema and rowCountHints, and mentions the output verdict. Lacks specifics on findings format but is adequate 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 description coverage is high (75%), and the description adds meaning by explaining that schema enables cost analysis and that rowCountHints affects cost estimates. The dialect is constrained to 'postgres' as per 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 analyzes Postgres SQL for destructive operations, locking risk, anti-patterns, and query cost, and returns a deterministic verdict. This distinguishes it from sibling tools which are policy-related.

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 include the optional schema for cost analysis versus static analysis only. It doesn't explicitly compare to siblings, but the context of policy tools makes the use case clear.

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

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

Discloses read-only behavior and empty list case, but lacks specifics on return format or structure of policies, though context from analyze_sql helps.

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?

Three sentences, front-loaded purpose, minimal yet informative, 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?

Adequate for a zero-parameter read-only tool; could optionally describe return format, but not essential given sibling context.

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?

No parameters, so schema coverage is 100%; description adds no param info but it is unnecessary.

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?

Clearly states it returns the custom org policy set, explicitly links to analyze_sql, and distinguishes from sibling set_policies.

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?

Explicitly describes when to use (retrieve current policies), notes read-only nature, and directs to set_policies for changes.

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

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

With no annotations, the description discloses key behaviors: the tool replaces the entire set, validates policies without executing them, and applies transparently to analyze_sql calls. It also mentions a maximum of 50 policies. It does not address authentication requirements, rate limits, or error handling scenarios.

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: four short sentences with clear structure. The first sentence states the core action, the second gives an example of a policy, the third clarifies behavior, and the fourth directs to a sibling. No extraneous content.

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 of the tool (nested policy objects, no output schema), the description explains the policy concept and its effect on analyze_sql. It mentions the Pro key requirement and validation. It could be more complete by noting the return value or potential errors, but it adequately covers the essential context.

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?

The schema provides full parameter names and types. The description adds semantic value by explaining that an empty array clears all policies, that the set is a replacement, and hints at the 'max 50' constraint. This goes beyond the raw 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 that the tool replaces, updates, or clears custom org policies for a Pro key. It specifies the verb 'Replace' and the resource 'custom org policy set', and distinguishes from sibling 'get_policies' by directing to read the current set.

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 how to update (send full new set) and clear (send empty array) policies, and references analyzing_sql as the context where policies apply. It tells when to use get_policies instead. However, it does not explicitly state when not to use this tool or mention alternatives for non-Pro users.

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