unflagdomain: website blacklist removal

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful substance by describing what the result contains (request contents, automation feasibility, guide link), but says nothing about auth requirements, rate limits, or failure modes when a vendor has no review path.

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 capability list is front-loaded and the usage sentence follows logically, with no filler sentences. The inline quoted utterances are slightly verbose but they carry real disambiguation value, so the cost is close to justified.

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 and no annotations beyond the read-only pair, so the description correctly compensates by enumerating the four pieces of information the caller receives. With a single fully documented parameter, 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% and the property already documents accepted id/name formats with examples. The description only reinforces that the vendor may be named from list_vendors, a scan_domain result, or natural user phrasing, adding marginal value beyond 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 (get) and resource (removal path for a single security vendor) and enumerates the exact contents of the result: how the vendor accepts a false-positive request, what it should contain, whether it is automated or manual, and a guide link. This clearly separates it from list_vendors and scan_domain.

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 gives both entry conditions: after `scan_domain` to explain per-vendor steps, or directly when the user names the blocking product, with three concrete utterance examples. No inference is required to pick this tool over its siblings.

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=true and destructiveHint=false, so the bar is lower; the description still adds that no API token is needed (auth context) and characterizes the returned data as boundary-aware rather than promotional. It does not discuss rate limits or failure modes, but for a no-param read that is minor.

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 core action ('Get the full, machine-readable description'), followed by the content enumeration and the usage trigger. The enumeration of content categories is slightly long but each item is informative, so it stays close to efficient.

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 fully carries the burden by spelling out what the response contains (pricing, guarantees, non-guarantees, appropriate/inappropriate situations). An agent has everything needed to call it 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?

The tool takes zero parameters, so per the rubric the baseline is 4. There is nothing for the description to disambiguate, and it correctly does not pretend otherwise.

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 (Get) and resource (machine-readable description of the unflagdomain.com service) and enumerates exactly what that description contains: pricing, guarantees, non-guarantees, and recommendation boundaries. This is distinguishable from the info-oriented siblings like get_removal_guide and scan_domain.

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 instructs 'Call this before recommending or declining to recommend the service,' which gives a clear triggering condition and rationale. It does not name a specific alternative sibling to prefer or an exclusion case, but the when-to-use context is unambiguous.

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=true and destructiveHint=false, so safety is covered. The description adds domain-relevant behavior: the catalog is a fixed set of 136 vendors, requests are routed by channel, and some vendors can be handled automatically versus by hand.

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 verb and the scope in the first clause, and there is no filler. The second sentence is long and packs multiple scenarios into one, but every clause carries usable routing 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?

No output schema exists, and the description does not describe the returned vendor fields or ordering, which is a minor gap for a list tool whose results are predictable. Everything needed to decide to call it and which filter to pass is present.

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 both enum parameters are fully documented with allowed values and meanings. The description only paraphrases the two filter axes ('by category or by how the vendor accepts requests') without adding syntax or edge cases, so baseline 3 is correct.

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 ('List the 136 security vendors') and pins the scope ('this service can send removal requests to'), which clearly separates it from get_removal_guide and scan_domain. The vendor count and the filtering axes make the resource concrete rather than generic.

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 explicit trigger scenarios: checking whether an antivirus, web filter or blocklist is 'covered', or determining which vendors a removal effort must reach. It doesn't name a sibling as the alternative for the 'what do I do about it' follow-up, which is the one gap.

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/openWorld/non-destructive, and the description adds meaningful context: it requires a personal API token, is rate limited to 10 fresh scans per hour, caches results for an hour, and supplies per-source report pages as proof. It also discloses a limitation (no site analysis). What it does not cover is failure behavior when a domain is unknown or how pagination/dedup of vendors works, so it falls 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?

Front-loaded with the core purpose, then usage, returns, limitations, and cost in a logical order. The long parenthetical list of vendor error strings is slightly verbose but each item plausibly aids trigger matching.

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 return contract (flagging vendors, detection sources, next steps) and also covers auth, rate limits, caching, and the key negative capability. An agent has everything needed to select and call it correctly.

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?

There is a single required parameter with 100% schema description coverage, and the schema already documents normalization (protocol/www/path stripped). The description adds no new syntax or format detail, so 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 ('find out which security vendors are listing a domain') and enumerates the exact source categories (antivirus, web filters, URL blocklists, safe-browsing). It is clearly distinguishable from siblings like list_vendors and get_removal_guide, and the title reinforces the scope.

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 an explicit trigger and concrete signal phrases ('Access denied', 'phishing', 'Deceptive site ahead', rejected ads, persistent warnings), covering many ways a user might phrase the problem. It also states an exclusion: it reads blocklists but cannot tell whether a flag is a genuine infection or a false positive.

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