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

The description adds useful context beyond the annotations: it discloses a cost ('$0.05'), a legacy/deprecated status, and a mandatory verification step. Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The added cost and workflow requirements are valuable behavioral details.

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 short (three sentences) and front-loaded with the key qualifier 'LEGACY taste only.' Each sentence provides a distinct piece of information: legacy status, price, alternative paths, and verification. There is no fluff, though the brevity contributes to the opacity rather than clarity.

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 provides pricing, legacy status, and a prerequisite, but it fails to explain what 'Instant Cert' actually does or when it should be invoked beyond vague 'legacy' scenarios. The output schema exists, so return values are not needed, but the overall purpose and usage context remain incomplete due to heavy jargon and lack of plain-language function.

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 input schema already provides 100% coverage, describing each parameter (sql, agent_id, schema_ddl) with clear definitions. The description does not add any additional parameter-level meaning, only mentions 'Exact' in relation to the cert, which is ambiguous. The baseline of 3 is appropriate because the schema carries the parameter-semantics burden.

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 never explicitly states what the tool does. It uses cryptic jargon like 'LEGACY taste only' and 'Instant Cert' without defining what a certificate is or what action it performs. The title says 'Instant Cert' but the description doesn't clearly say 'issues a certificate for SQL' until you cross-reference the schema fields. As a result, an agent cannot confidently infer the tool's core function from the description alone.

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 gives explicit guidance on when NOT to use this tool: it's 'LEGACY taste only' and 'OFF TABLE as wealth/primary,' pointing to alternative wealth paths via sqlguard_challenge or Gateway. It also instructs to use sqlguard_verify before execute. This provides a clear conditional context, even though the phrasing is obscure.

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