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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds a genuinely non-obvious behavioral trait: a domain is reported as listed even if only a parent domain is on the list. It does not mention rate limits or the VirusTotal enrichment path whenever enrich is used.

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 efficient sentence with the primary behavior front-loaded and the parent-domain caveat trailing as a qualifier. No filler or redundancy.

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?

An output schema exists, so return values need not be explained. The description conveys what is checked and the parent-domain nuance, which covers the core behavior. It leaves the choice among sibling check tools unaddressed, a minor gap.

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 (domain including IDN, enrich with its API-key requirement) are fully documented in the schema. The description adds nothing about parameters, which is acceptable given full schema coverage and yields the baseline score.

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: check whether a domain is listed by USOM. The mention of parent-domain listing further sharpens scope. It does not explicitly contrast itself with siblings check_url or check_ip, but the domain-specific framing makes the resource clear.

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?

No statement of when to use this tool versus check_url, check_ip, or watch_check. There are no prerequisites or exclusions mentioned. The agent must infer usage purely from the name and resource type.

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 establish readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context by identifying the data source (USOM) and the matching semantics (exact or inside a listed network), though it does not mention external API dependencies or rate limits for the optional enrichment 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 description is a single front-loaded sentence that states the tool's action and its two matching modes. There is no wasted text.

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?

Given the existing output schema and annotations, the description is nearly complete: it identifies the source and matching behavior. A minor gap is that it does not mention the optional external enrichment behavior, though the schema already documents that parameter and its API-key requirement.

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 are already documented in the schema, including the enrich flag and its API-key requirement. The description does not add param-level syntax or format details beyond the schema, so the baseline of 3 is appropriate.

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 states a specific verb and resource: check whether an IP address is listed by USOM. It also specifies the scope of matching (exactly or inside a listed network), which distinguishes it from related check_url and check_domain siblings without ambiguity.

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 purpose: use this when checking an IP address against USOM. However, the description does not explicitly say when to prefer this over check_domain, check_url, or search_threats, nor does it mention exclusions or prerequisites.

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 openWorldHint=true, so safety is covered. The description adds matching semantics (exact, parent-domain, URL path, CIDR) and names the result fields (match type, date, source, category), which go beyond annotations, though no auth or rate-limit details are provided.

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 plus a parenthetical, front-loaded with purpose and then the usage trigger. Every sentence earns its place with no redundant framing or 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 an output schema, read-only and open-world annotations, and full parameter descriptions, the definition supplies the purpose, trigger, match semantics, and result composition an agent needs. Nothing material is missing for a read-only lookup tool.

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 both parameters are fully documented in the schema. The description adds no syntax, format, or usage detail for 'url' or 'enrich', so the schema carries the parameter semantics.

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 ('Check whether') and resource ('a URL'), plus the four match types (exact, parent-domain, URL path, CIDR). It does not name or contrast with sibling tools such as check_domain or check_ip, so sibling differentiation relies on the resource name alone.

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 says 'Call this first when a user asks whether a link is safe,' giving a clear trigger condition. It offers no when-not guidance or alternatives for domain/IP checks, so it provides context without exclusions.

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 openWorldHint=true, so safety and external-data scope are covered. The description contributes the result ordering, which is useful behavioral context, but says nothing about result volume, pagination, or what a 'USOM record' contains.

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 short sentence with the ordering constraint front-loaded and no filler. Nothing to trim.

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 an output schema present and annotations covering the safety profile, the description only needs to convey scope and ordering, which it does. The remaining gap is the lack of any sibling differentiation against search_threats.

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 type/limit/category all documented in the schema including enum values and the 1-200 bound. The description adds no parameter-level detail, so the schema does all the work and 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 verb and resource ('Return the most recently added USOM records') and adds the ordering guarantee ('newest first'), which is genuinely informative. However, it never distinguishes itself from the sibling search_threats, so an agent must infer the difference from the name alone.

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 phrase 'most recently added ... newest first' implies this is the tool for chronological/recency browsing rather than targeted lookup, which is usable guidance. But there is no explicit when-to-use statement, no mention of the alternative search_threats, and no exclusions, so the routing decision is left to inference.

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 openWorldHint=true, so the safety profile is covered. The description adds nothing behavioral beyond that—no pagination/default-limit behavior, no indication of result ordering or scope limits across the USOM list.

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 short sentence with the resource and filter axes front-loaded and no wasted words. It is efficient, though terseness here shades into under-specification rather than elegance.

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 an output schema present, return values need not be explained, and the schema fully covers parameters. However, for a 10-parameter open-world search tool, the description omits practical context such as paging behavior, default page size, and how it relates to sibling search tools.

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 all ten parameters are already documented with formats, enums and ranges (e.g., source codes, date formats, criticality direction). The description only gestures at the same filter axes, adding no syntax or semantics 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 ('Search') and resource ('the USOM list') plus the filter axes it accepts. It is clear about what the tool does, but it never names or distinguishes itself from siblings like latest_threats, which also surface threat data.

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?

No when-to-use guidance is given: it does not say when to prefer this over latest_threats or the check_* lookup tools, nor when a search is inappropriate. The filter list implies usage but leaves the agent to infer routing.

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 openWorldHint=true, so the safety profile is covered. The description adds useful content context (what data the cache/index exposes), but says nothing about freshness guarantees, cost, or whether the stats reflect the same source the sibling lookups query.

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, front-loaded with the action and then the four returned fields. Every word 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?

For a zero-parameter, read-only status endpoint with an output schema already present, the description is nearly sufficient. Only the missing guidance on when to consult stats (and how it relates to the sibling lookups) keeps it from being fully complete.

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 of 4 applies. The description correctly does not invent any parameter discussion, and the schema's additionalProperties:false is consistent with the parameterless call.

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?

Names a specific verb (Report) and enumerates the exact data points returned: record counts, newest record date, last sync time, cache status. Clearly distinguishable from the threat-lookup siblings, which all deal with individual indicators rather than cache/index metadata.

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?

No statement of when to prefer this over siblings or what situation calls for a stats check (e.g. diagnosing stale cache before a search returns nothing). Usage is only inferable from the 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 idempotentHint=true and openWorldHint=false, so the safety/repeat behavior is covered. The description adds the genuinely useful scope detail that entries go to a 'local' watch list rather than a shared one, but says nothing about how duplicate entries are reconciled or whether additions are persisted across restarts.

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 front-loaded sentence with the verb first and zero filler. Nothing in it is redundant with the name or schema, and nothing is padded.

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?

An output schema exists, so return values need no explanation, and the input surface is trivial (one required array plus an optional label). Still, for a mutation-style tool the definition omits the preconditions and follow-up actions an agent would want, leaving it merely adequate.

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 (label, values) are already documented in the schema; the baseline is 3. The description loosely corroborates the 'values' parameter by naming domains/IPs/networks, but contributes no syntax, format, or label semantics 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?

Specific verb ('Add') plus resource and target ('your own domains/IPs/networks to the local watch list'), so the operation is unmistakable. It does not explicitly name or contrast with the nearest siblings (watch_remove, watch_list, watch_check), but the add/remove/list distinction is self-evident from the wording.

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 when-to-use guidance, no prerequisite or exclusion, and no routing to alternatives such as watch_check (to test an entry now) or watch_list (to inspect existing entries). Usage is only implied by the verb 'Add'.

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 provide only openWorldHint=true, so the description carries most of the behavioral burden. It usefully discloses that domains report listed subdomains and that each item shows what is new since the previous check, but it does not state read-only status, authentication requirements, rate limits, or side effects. The added output behavior is helpful but incomplete.

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 description is short and front-loaded around the core action. The second sentence about new items and the subdomain note are useful but slightly clipped, leaving them a bit cryptic rather than wasteful.

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?

An output schema exists, so the description does not need to enumerate return values, and it still adds relevant behavioral context about deltas and subdomains. However, for an open-world scan tool with minimal annotations, it leaves out important operational context such as permissions or expected scan scope beyond the watch list.

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 single optional parameter already documents that omitting value scans the entire watch list. The description adds no further parameter syntax, filtering, or formatting details beyond what the schema provides, 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?

The description states a specific verb and resource: scanning the watch list against USOM. It adds useful scope details, including subdomain reporting and delta reporting since the previous check. It does not explicitly distinguish itself from siblings such as watch_list, but the purpose is clear without 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?

The description does not explain when to use this tool versus alternatives like watch_list, check_domain, or check_url. The only usage-like guidance is embedded in the parameter schema, which says to omit value to scan the whole list; that is parameter behavior, not tool selection 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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds only that the list is 'local', which mildly reinforces the no-external-calls signal but says nothing about result size, ordering, or pagination 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?

A single front-loaded sentence with no filler; the verb and scope come first. Nothing in it is wasted or repeated.

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 an output schema present, return-value detail is unnecessary, and the description supplies the one thing structured fields cannot: that this enumerates the entire local list. It could be stronger by contrasting explicitly with watch_check, but nothing essential is missing for a zero-parameter read tool.

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, which is the baseline-4 case. The description correctly implies no filtering or arguments are needed to enumerate the list.

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 ('List') and resource ('local watch list'), and the word 'everything' signals full enumeration rather than a targeted lookup. The meaning is clear against siblings like watch_add/watch_remove, though the description never explicitly names an alternative to contrast with.

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 rather than stated: an agent can infer this is for browsing the whole watch list versus watch_check for a single entry. There is no explicit when-to-use guidance, no exclusions, and no named alternative.

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 disclose destructiveHint=true, idempotentHint=true, and openWorldHint=false. The description adds no behavioral context beyond that, such as what happens to missing entries, whether the operation is silent, or any rate 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?

The description is a single, front-loaded sentence with no unnecessary words. It is appropriately sized for the tool's simplicity.

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?

Given the simple one-parameter schema, existing output schema, and annotations covering safety, the description states the core action. However, it omits usage guidance and sibling differentiation, leaving some contextual gaps.

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 single parameter is fully documented in the schema. The description repeats the schema's meaning without adding syntax, limitations, or format details, so the baseline of 3 is appropriate.

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 states a specific verb and resource: remove entries from the local watch list. It is clear what the tool does, but it does not explicitly distinguish itself from related siblings such as watch_add or watch_list.

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 use this tool, when not to use it, or which alternatives to prefer. The description only restates the action without providing context for invocation.

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