Real Crypto Signals: crypto scam warning lists

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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real value: legal suffixes are normalized away before matching, and results are the closest N entries rather than exact matches — a fuzzy-match caveat the agent needs to interpret hits correctly.

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 waste, front-loaded with the action and scope, then the return shape. Nothing could be cut without losing 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 output schema, the description correctly covers what comes back (entries, warning regulators, notice URLs) and both parameters are accounted for. Missing only supporting detail such as what an empty result means or how match confidence is ranked.

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 only 50% (limit has no description), but the description compensates by explaining that limit caps returned closest entries and by documenting the name normalization rule. It meaningfully supplements rather than repeats the schema.

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: search the compiled regulator warning lists for a firm/brand/platform name. The name-based input distinguishes it implicitly from check_website, but no sibling is named, so the agent must infer the split itself.

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 only implied — an agent with a name in hand can deduce the trigger, but there is no explicit when-to-use statement and no comparison to check_website, latest_warnings, or list_sources. The most likely confusion (name search vs website check) is left unaddressed.

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 openWorldHint=false, so the safety profile is covered. The description adds genuinely non-derivable context: the lists are Real Crypto Signals' compiled regulator warnings, the return fields are named, and the 'empty result does not mean the site is safe' caveat prevents a false-negative interpretation. It stops short of stating list freshness or coverage limits.

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 sentences, zero filler, ordered input → output → interpretation caveat. The most decision-relevant caveat is placed last for emphasis without burying the core purpose.

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 one parameter, a fully documented schema, and no output schema, the description supplies exactly the missing pieces: accepted input formats, the shape of a match, and the critical caveat about empty results. Nothing needed to call or interpret the tool is absent.

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 documents maxLength/minLength/format, so the baseline is 3. The description goes beyond it by giving concrete accepted input shapes ('example-trade.com' or 'https://app.example-trade.com/login'), which resolves the practical ambiguity of whether a scheme or subdomain is needed.

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?

'Look up a website or URL ... in the official regulator warning lists' is a precise verb+resource+scope, and the named example inputs make the target unambiguous against the sibling check_name. It also states what is returned, so the agent knows the resource class and the value of the call before opening the 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?

Usage context is clear: check a site or domain against warning lists, with concrete example inputs showing both bare-domain and full-URL forms. It doesn't explicitly route against siblings such as check_name or latest_warnings, so the when-not-to-use side is inferred rather than stated.

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 this as a readOnly, idempotent, non-destructive, closed-world lookup, so the safety profile is covered. The description adds value beyond that by disclosing the return content — agencies with their official URLs — which matters given there is no output schema. It stops short of noting coverage gaps or fallback behavior.

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 tight sentences, front-loaded with the tool's purpose followed by input format and return shape. No filler or restatement of the title.

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 single-parameter, read-only lookup with no output schema, the description supplies both the input encoding (with examples) and the shape of the result. Nothing an agent needs to invoke it 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 coverage is 0% (the 'country' property has no description, only length constraints), so the description must carry the burden. It does: it names the ISO 3166-1 alpha-2 format and supplies ten concrete examples, resolving the main ambiguity for a 2-character string parameter.

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 — finding official reporting places for a crypto/investment scam — with the scoping dimension (country) made explicit. It is clearly distinguishable from siblings like check_name, check_website, and latest_warnings, which are lookups rather than reporting-routing tools.

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 implies the trigger context (you need somewhere to report a scam) and gives the required country format, but never states when to prefer this over the check_* siblings or what happens when a country has no listed agencies. Usage is implied rather than directed.

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, idempotentHint, non-destructive and openWorld=false, so the safety profile is covered. The description adds the result ordering (newest first) and the notion of 'compiled lists', but says nothing about pagination, how many results to expect, or the default limit behavior.

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 filler, and the core behavior (newest warnings, newest first) is front-loaded before the optional filters. Every clause earns its place.

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?

There is no output schema, so the description should ideally hint at what a warning record contains and how many are returned by default, neither of which is stated. It is adequate for invoking the tool correctly but leaves the result shape to inference.

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 0%, so the description carries the burden: it explains that regulator is a code sourced from list_sources and that country is an ISO 2-letter code, with six concrete examples. The third parameter, limit, is left entirely to the schema, so the compensation is partial but real.

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 (newest warnings added to the compiled lists) and ordering (newest first), which is unambiguous. It cross-references list_sources for regulator codes, giving some differentiation from siblings, but never contrasts itself with check_name or check_website, which also deal with regulators.

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 implies when to use the filters (optionally by regulator or country) and points to list_sources as the place to obtain regulator codes, which is a useful routing hint. However, there is no explicit statement of when this tool is preferred over check_name/check_website or when filtering is required.

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, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds useful value by enumerating the returned fields (counts, URL, fetch timestamp) with no output schema present, but discloses nothing about ordering, caching, or freshness guarantees.

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 tight clause with no filler, and the returned-field list is front-loaded. It is a noun fragment rather than a sentence, which costs a point on readability but wastes nothing.

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 input parameters and no output schema, the description carries the return-value burden and does so by listing the fields an agent will receive. For a simple read-only inventory tool with full annotation coverage, this is sufficient, though a note on use case would round it out.

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 the baseline is 4. The schema has no parameters to document and the description introduces no misleading parameter-like concepts.

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 identifies the resource — the official warning lists ('sources') and the data reported for each: entry counts, list URL, and last-fetch time. It does not name an action verb ('list'/'return') nor distinguish itself from siblings like latest_warnings, but the subject matter is 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?

There is no guidance on when to call this versus alternatives. Given four sibling tools (check_name, check_website, latest_warnings, how_to_report), an agent gets no signal about whether this is for provenance/audit purposes versus actual lookups.

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