Canisell

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

Goes well beyond the readOnly/idempotent annotations by disclosing the paid model ($0.01 USDC per call via x402) and, critically, the degraded behavior when no wallet is present (payment terms and paid HTTP URL instead of a verdict). It also enumerates what the verdict covers and the return shape (SAFE/CAUTION/DANGER, 0-100 score, reasons), which is exactly the context an agent needs before incurring a cost.

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-loads the verdict purpose, then the checks, then the cost and payment fallback — a sensible priority order. The parenthetical check lists are dense but each element is informative; only the 'Not financial advice' tail is marginal.

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 still communicates the return values (verdict tier, score, reasons) and the non-verdict payment response. Cost, scope, and failure mode are all covered, leaving nothing an agent needs before calling it.

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?

Single parameter with 100% schema description coverage including the address pattern and Base mainnet chain. The description adds no parameter-level detail beyond the schema, so the baseline of 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 deliverable ('Pre-trade risk verdict') for a specific resource (Base ERC-20), with a named target segment (brand-new Clanker/Zora/Uniswap v4 launches) and the checks performed. It doesn't explicitly contrast itself with the sibling get_token_info, which is the closest alternative, so it falls short of full sibling differentiation.

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 context is clear: pre-trade due diligence on freshly launched tokens, plus an explicit fallback path for MCP clients without an x402 wallet. It stops short of naming when-not-to-use or directing agents to get_token_info/explain_verdict_fields for narrower needs.

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?

The annotations already cover the safety profile (readOnly, idempotent, non-destructive, not open-world), so the bar is lower. The description still adds genuinely non-annotated context: the tool is free and it also discloses the limits of the checks themselves, which is useful for calibrating trust in the sibling verdict tools.

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?

A single compact fragment with the cost qualifier front-loaded and the covered topics enumerated in descending order of usefulness. It is slightly clipped (no main verb, list-like), but nothing in it 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?

For a zero-parameter, no-output-schema documentation tool, the description covers enough to know what the response will teach. The one gap is that it does not say whether the answer is general reference material or must be paired with a specific verdict from another call, which an agent may need to know before invoking it.

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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. If anything the wording 'each field of a verdict' could briefly suggest a verdict input exists, but the empty schema resolves that immediately.

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 names a specific verb+resource (explain verdict fields) and enumerates the exact topics covered: SAFE/CAUTION/DANGER meanings, score, per-field meaning, check limits, prices, JSON schema. It reads clearly as reference documentation, distinct from the check/get siblings, though it never explicitly contrasts itself with them.

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?

'Free.' is a soft usage cue implying this is the no-cost option when you only need to interpret an existing verdict rather than run a check. However, it never states when to call this versus check_base_token or get_sample_verdict, leaving that routing to inference from the tool name.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: it is free, it is cached (i.e., fixed/stale data, not a fresh computation), and it reflects one specific real Base token rather than the caller's input. That 'cached' disclosure is the most useful thing here.

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?

One sentence, no filler, and the cost differentiator ("Free.") is front-loaded ahead of the explanation of what is returned. Every clause carries information.

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 parameters and no output schema, the description does enough: it says what the payload is a sample of and why it exists. The one remaining gap is that it never says which token the sample covers or that the data is static, so an agent cannot tell whether the sample is representative of a specific verdict type.

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?

Zero parameters, so baseline is 4. The description implicitly reinforces this by framing the tool as returning a fixed example rather than something parameterized, leaving no ambiguity about why the schema is empty.

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 resource (a cached example of the check_base_token response) and explicitly distinguishes it from the paid sibling by naming check_base_token and calling this an example of its output. An agent can tell instantly that this is a preview, not a live lookup.

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?

"To see the shape before paying" gives a clear condition for use: call this first to learn the response format, then move to the paid check_base_token. It does not mention when NOT to use it (e.g., when you need a verdict for an arbitrary token, use check_base_token or get_token_info instead), so it stops short of full routing guidance.

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 cover read-only, idempotent and open-world behavior. The description adds useful context beyond them: price tier (free vs paid sibling) and the deliberate absence of risk scoring. It stops short of saying what is returned when an address is not a contract or not an ERC-20, which would matter for interpretation.

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 short sentences, front-loaded with the 'Free' qualifier and the core purpose, then the returned fields, then the sibling routing. No filler.

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 does list the meaningful return fields and the routing alternative, which is the main thing an agent needs. It is slightly incomplete in not describing the response for non-ERC-20 or EOA addresses (e.g., whether fields are null or omitted).

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%: the single address parameter is fully documented including the 0x pattern and Base mainnet chain. The description only repeats the chain context and adds no syntax or semantic detail beyond the schema, 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 check (contract vs ERC-20 on Base mainnet) and the exact metadata returned (name, symbol, decimals, total supply). It distinguishes itself cleanly from check_base_token by explicitly excluding risk analysis.

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 frames itself as the free metadata path and names the paid alternative check_base_token with the condition that selects it (SAFE/CAUTION/DANGER verdict). The exclusion ('No risk analysis') removes ambiguity about which sibling to call.

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