Token Risk Checker

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

Annotations already declare readOnlyHint and openWorldHint, so the safe-read profile is covered. The description goes further by disclosing the return surface (0-100 score, LOW/MEDIUM/HIGH level, per-check reasons) and an important scope caveat that this is an automated screen rather than an audit. It does not mention rate limits, latency, or unsupported tokens, keeping it short of a 5.

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?

Purpose and scope are front-loaded in the first clause, and the long checklist of checks is dense but each item maps to a distinct risk category. The trailing sentence cleanly caps expectations. Slightly overlong as a single breath, but nothing is wasted.

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 naming the returned score, level, and per-check reasons, and by bounding the tool's authority as a screen not an audit. This is close to complete for a 2-parameter read-only tool; only the sibling routing detail 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% with only two parameters, so the schema already documents the address pattern and the base-only chain enum. The description adds no parameter-level syntax beyond the general 'Base token' scope, which matches the baseline 3 when the schema does the heavy lifting.

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 ('Full risk report for a Base token') and enumerates the exact checks it performs, so the agent knows precisely what output to expect. The word 'Full' implicitly contrasts with the sibling quick_token_risk, but the sibling is never named, so the differentiation is inferable rather than explicit.

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?

Usage is implied by the 'Automated risk screen, not a security audit' disclaimer, which usefully bounds expectations, but there is no explicit when-to-use guidance, no exclusion criteria, and no pointer to quick_token_risk as the cheaper alternative. The agent must infer routing from the word 'Full' alone.

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?

Annotations already declare readOnlyHint and openWorldHint, and the description adds real signal on top: the full list of checks run, the return shape (0-100 score, LOW/MEDIUM/HIGH level, per-check reasons), and an explicit caveat that this is a screen rather than an audit. It does not mention latency, rate limits, or behavior on unverified/invalid contracts, which is the remaining gap for an open-world lookup tool.

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, zero filler. The core capability and the sibling comparison come first, and the scope disclaimer is placed last where it reads as a caveat rather than a hedge.

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 carries the burden of describing returns, and it does: score range, severity level, and per-check reasons. Combined with the enumerated checks and the audit disclaimer, an agent has everything needed to call this confidently and interpret the result.

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 the address pattern and the chain enum are already fully documented structurally. The description reinforces that the target is a Base token, which aligns with chain being defaulted/locked to base, but adds no format, aliasing, or validation nuance beyond the schema. 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 and resource ("quick risk check for a Base token") and enumerates the concrete checks performed, so the agent knows exactly what signal it gets. It explicitly positions itself against the sibling by saying "the same checks as check_token_risk ... without the AI summary," making the two tools trivially distinguishable.

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 comparison to check_token_risk implies the selection rule: use this when the raw score and per-check reasons suffice, use the sibling when an AI summary is wanted. The closing line "Automated risk screen, not a security audit" scopes expectations. It stops short of an explicit "use X when..." statement or any exclusion for non-Base chains beyond the tool's framing.

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