Veto — SQL Safety & Cost Oracle

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

With no annotations, the description discloses deterministic verdict (ok/warn/block) and that cost analysis uses a throwaway Postgres instance. It does not mention side effects or permissions, but as a read-only analysis tool, this is adequate.

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-loaded with purpose, then key detail on optional schema. No wasted words, every sentence adds value.

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 no output schema, the description covers input, behavior, and output type (verdict with findings). It does not detail findings structure, but is sufficient for agent use.

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 description adds meaningful context beyond the schema: explains schema parameter enables cost analysis, sql accepts multiple statements, and rowCountHints is for realistic estimates. Schema coverage is 75%, and the description compensates well.

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 defines the tool as analyzing Postgres SQL/migrations for specific issues (destructive operations, locking, correctness traps, etc.). It distinguishes from siblings (get_policies, set_policies) which serve different purposes.

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 use static vs. cost analysis based on the schema parameter. It does not explicitly state when not to use or provide alternatives to other SQL analysis tools, but siblings are unrelated.

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 provided, the description fully discloses behavioral traits: read-only, returns empty list if none set, and ties the data to the Pro key. No contradictions present.

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, no wasted words. The description is front-loaded with the main action and efficiently conveys purpose, usage, and behavior.

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?

For a zero-parameter, no-output-schema tool, the description covers all necessary aspects: what it returns, read-only nature, empty list case, and relationship to sibling tools. No gaps.

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?

There are no parameters, and the schema coverage is 100%. The description adds value by explaining what the tool does and its context beyond the schema (e.g., Pro key, relationship to analyze_sql).

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 returns the custom org policy set for a Pro key, and explicitly distinguishes it from siblings by mentioning 'Read-only' and directing to set_policies for changes. The verb+resource is specific and unambiguous.

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 explicit guidance: use to view policies, not to change them (use set_policies). It also clarifies the relationship with analyze_sql, giving context for when this tool is relevant.

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?

No annotations provided, but the description fully discloses behavioral traits: policies are declarative data, validated but never executed, they replace previous set, apply transparently to later analyze_sql calls, and have a max of 50 policies. No contradiction.

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?

Four sentences, front-loaded with the primary action, no redundant words. Every sentence adds unique value: action, update/clear mechanism, policy semantics, side effects, and reference to sibling tool.

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 only one parameter with full schema coverage and no output schema, the description completely covers usage, behavior, and relation to sibling tools. No gaps.

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% and the schema already describes the parameter structure well. The description adds value by explaining how to update (send full set) and clear (empty array), which goes beyond the schema's description. This additional usage context justifies a score above the baseline of 3.

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 action ('Replace the stored custom org policy set') and the resource ('for your Pro key'). It distinguishes from sibling tools by mentioning get_policies for reading and analyze_sql for applying 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?

Provides explicit when-to-use context: setting, updating, clearing policies. Gives example of behavior (blocks/warns on operations) and tells user to use get_policies for reading. No ambiguity.

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