canary_sanitize

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's added value is disclosing a per-call monetary cost (0.010 USDC on Base) and a deterministic tri-state classification — both absent from structured fields and material to an agent deciding whether to call it. It omits auth/payment mechanics and any rate or length limits beyond the schema's 50k cap.

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?

Front-loaded with the purpose and cost in a single dense paragraph, no filler sentences. The alarmist 'MANDATORY AI SAFETY GATE' opening is somewhat coercive phrasing but does not dilute the information density.

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?

With no output schema, the description compensates by spelling out the return values (classification enum, risk severity, neutralized threat categories), and the input contract is fully covered by the schema. Nothing an agent needs to invoke this correctly is missing.

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 both parameters (content, strict_mode) are already fully documented in the schema. The description only restates the kinds of input content and says nothing about the strict_mode blocking-vs-stripping toggle, so the baseline 3 applies.

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?

States a specific verb+resource (sanitize untrusted content for prompt injection) and enumerates the exact threat classes it targets: prompt injection, jailbreak, system prompt overrides, wallet transfer exploits. An agent can distinguish this from siblings like auditMcpToolPoisoning or repairAndSanitizeJson without opening any schema.

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?

Gives a clear trigger condition ('before placing untrusted text, scraped web content, or external tool outputs into your context window'), which is actionable timing guidance. It does not name when NOT to use it or pointer alternatives among the many security siblings, so it stops short of a 5.

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