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

No annotations are provided, so the description carries full burden. It discloses validation, backend specifics (Hybrid Analysis, MalwareBazaar), the cap, and a security warning about untrusted data. It lacks details on rate limits or authentication, but the security note adds value.

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 concise, using three short paragraphs. The first sentence front-loads the purpose. Every sentence adds value: validation details, backend info, cap, security note. No redundant or filler words.

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 presence of an output schema (which likely explains return values), the description sufficiently covers input, behavior, and security considerations. It is complete for a bulk-lookup tool with one parameter.

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 input schema has 100% coverage with a description for the 'hashes' parameter. The description adds further meaning by specifying accepted hash types (MD5/SHA1/SHA256) and the maximum of 50 processed, which goes 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?

The description clearly states 'Look up many file hashes at once across enabled hash-intel backends', specifying the verb and resource. It distinguishes from sibling tools like search_hash (single hash lookup) by emphasizing 'many' and 'at once'.

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 provides context for when to use (bulk lookup) and explicitly mentions a cap of 50 hashes. However, it does not explicitly state when not to use or name alternatives, though the context of siblings implies it.

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?

With no annotations provided, the description carries full burden. It discloses that the tool returns a yes/no with per-source provenance, mentions authentication requirements for certain sources, and includes a security warning about untrusted data. It does not cover error handling or rate limits, but the behavioral disclosure is adequate.

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 well-structured across three short paragraphs: first defines purpose, second details sources and authentication, third adds security warning. It is front-loaded with the core action and contains no unnecessary words.

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 tool has a single parameter and an output schema (context signals indicate output schema exists), the description provides sufficient context: what it checks, which blocklists, authentication needs, and data trustworthiness. No additional context is needed.

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 input schema has 100% coverage with a single parameter 'indicator' and its description. The tool description reiterates the same information (IP, domain, URL) without adding new semantic context beyond what the schema provides. Baseline 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 clearly states the tool checks whether an IP/domain is a known botnet C2, lists specific blocklists (Feodo, ThreatFox, URLhaus), and mentions the return type (yes/no with provenance). It distinguishes from sibling tools like enrich_ioc or scan_url by focusing on C2 intelligence.

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 implicitly defines usage for C2 checking and notes key requirements (Feodo no API key, ThreatFox/URLhaus need configured key). However, it does not explicitly state when to use this tool over alternatives or provide exclusion criteria.

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?

With no annotations provided, the description bears full responsibility for behavioral disclosure. It reveals concurrency across multiple backends, normalization into triple, consensus with disagreement notes, and includes a security warning about untrusted vendor data. It does not cover rate limits or error handling, but these are partially mitigated by the presence of an output schema.

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 well-structured, with the main action in the first sentence, followed by process details and a security note. It is appropriately sized for the complexity and front-loaded, though it could be slightly more concise without losing meaning.

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 tool's complexity (multi-source, concurrency, consensus), the description covers the key aspects: sources, normalization, consensus, and security. The existence of an output schema reduces the need to explain return values. Minor gaps like timeout or failure handling are acceptable for a comparison tool of this nature.

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 single parameter 'hash' is fully described in the input schema (MD5, SHA1, SHA256 hex digest). The description adds no additional semantic value beyond what the schema provides, so the baseline score of 3 is appropriate given 100% schema coverage.

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 states the verb 'compare verdicts', the resource 'one file hash', and the scope 'across every enabled source'. It lists specific backends (Hybrid Analysis, MalwareBazaar, tria.ge, VirusTotal) and explains the normalization and consensus process, effectively distinguishing it from sibling tools like search_hash or bulk_hash_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?

The description provides clear context on when to use the tool: to compare verdicts from multiple sources for a single hash. While it does not explicitly state exclusions or alternatives, the unique cross-source functionality is implied, and the sibling list offers alternatives for single-source or bulk lookups.

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?

No annotations provided, so description carries full burden. Discloses critical behavioral traits: writes to quarantine directory, never executes/unpacks/opens, risk of live malware, and the two-step gate process. This is exceptionally transparent.

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?

Extremely concise with only a few sentences, front-loaded with purpose. Uses emphasis (DANGER, NEVER, REFUSES) to highlight critical warnings without extra words.

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 a high-risk tool with no annotations but with output schema, the description covers safety, gate process, and destination (SANDBOX_ARTIFACTS_DIR). Could optionally mention what to do after download, but not essential.

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%, baseline 3. Description adds value by explaining the acknowledge_malware_download parameter's role in the gate process, beyond the schema's default and required status. The other parameters (target, sandbox) are well-described in schema without duplication.

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 states the tool downloads a malware sample to disk for offline analysis, using specific verbs ('Download') and resources ('malware sample'). It distinguishes itself from siblings like search_samples and submit_sample by focusing on downloading and the GATED mechanism.

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?

Provides clear instructions on when to use: requires acknowledge_malware_download flag and describes a two-step process (first without flag, then with flag after user confirmation). Does not explicitly compare to alternatives but the context of danger and isolation is strong 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?

No annotations provided, so description carries full burden. It discloses concurrent and fault-tolerant fan-out, folding responses into one verdict with malware families, C2 flag, and references. Also includes a security warning about untrusted data. This is thorough behavioral context.

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 paragraphs: concise first sentence, detailed second paragraph, security warning third. Informative but could be streamlined. No redundancy, but some details (like source names) could be integrated more succinctly.

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?

Output schema exists, so description doesn't need to detail return values. It explains the output includes verdict, malware families, C2 flag, references, and trustworthiness. For a single-parameter tool with output schema, this is quite 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?

Schema coverage is 100% with a single parameter. Description adds the types (IP, URL, domain, hash) which matches schema. Adds context about classification and fan-out, but not significantly beyond schema. Baseline 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?

Description clearly states the verb 'enrich' and resource 'one indicator (IP/URL/domain/hash)' across all intel sources. It distinguishes from siblings like bulk_hash_lookup by focusing on single IOC enrichment from multiple sources.

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?

Description provides context on what the tool does (enriches one indicator, fans out to multiple sources) but does not explicitly state when to use it versus alternatives like check_c2_blocklist or compare_verdicts. There are no exclusions or when-not instructions.

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?

With no annotations, the description carries full burden. It details the pipeline (normalize, ATT&CK-enrich), format version (v4.5), output artifact (JSON), returned fields (path, count), and inlining for small layers. It also discloses the security concern about UNTRUSTED labels. Missing details like error handling or prerequisites, but sufficient for typical use.

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 concise (6 sentences) and well-structured, leading with the main action. Every sentence adds value: export purpose, pipeline, format, artifact, and security note. No 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?

Given the tool's moderate complexity and that an output schema exists, the description covers all necessary aspects: action, process, format, artifact storage, and security. It is complete for an agent to understand usage and expectations.

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 schema covers the single parameter (task_id) completely with a clear description. The tool description adds context by noting it is a sandbox job ID from a finished report, but this is marginal beyond the schema. Baseline 3 is appropriate given 100% schema coverage.

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 states the tool exports a report's MITRE ATT&CK techniques as a Navigator layer file, specifying verb (export), resource (report's ATT&CK techniques), and output format (Navigator layer). It distinguishes from siblings like get_report and export_iocs by defining a unique output.

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 (when Navigator layer output is needed) and includes a security note about UNTRUSTED data. However, it does not explicitly state when not to use or mention alternatives beyond the implicit contrast with get_report.

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?

Given no annotations, the description carries full burden. It discloses that files are saved to disk with only metadata returned, and includes a security warning about untrusted data. This is clear behavioral context.

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 concise with three clear sentences covering purpose, behavior variations, and security. No extraneous 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?

The description covers purpose, behavior, and security. Since an output schema exists, return values are not needed. It does not mention prerequisites or error conditions but is sufficient overall.

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%, so baseline is 3. The description does not add new meaning beyond the schema for format and task_id, though it provides backend-specific context for format.

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 states the tool exports IOCs from a finished report to a structured intel file on disk, with specific verb+resource. It distinguishes between backends and mentions the security aspect, making it distinct from sibling 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 explains the tool's basic use case but does not explicitly guide when to use it over alternatives or when not to use it. Sibling tools are listed but no comparisons are made.

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?

No annotations provided, but the description fully discloses behavior: single poll, attaches raw vendor document, and warns that vendor strings are untrusted. It also specifies which backends apply.

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?

Very concise, uses clear sections and bullet points. Every sentence adds value without 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?

Given the output schema exists, the description covers all necessary aspects: purpose, usage, behavioral traits, and security. No gaps remain.

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 already covers the single parameter with a description. The description adds the format '<sandbox>:<job_id>' and source (from submit_sample), providing useful context 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?

The description clearly states the tool retrieves the live lifecycle state of a detonation job via a single poll. It distinguishes itself from siblings like get_report by specifying it avoids fetching the full report and only returns the state and raw vendor document.

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 states when to use (inspect why a job is stuck or check child tasks) and when not to (intel sources have no analysis lifecycle). Also contrasts with get_report.

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?

Discloses that the archive is saved to disk, never extracted, and may contain live malware. Includes security warning about attacker-controlled data. No annotations to contradict.

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 well-structured paragraphs with front-loaded main purpose. Each sentence adds value, though could be slightly more concise.

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 fully covered by schema and output schema present, the description explains the output behavior and security considerations adequately.

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%, so baseline 3 is appropriate. Description does not add additional meaning 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?

Clearly states 'Download the dropped/created files archive for a finished detonation' with specific verb and resource. Distinguishes from siblings by noting only Hybrid Analysis has this endpoint.

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?

Provides context of when to use (finished detonation) and backend-specific behavior. Lacks explicit when-not-to-use statements but implies through security warnings.

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?

No annotations exist, so the description carries the full burden. It discloses that the full content is saved to disk, never inlined, and includes a security warning about untrusted data. This goes beyond the schema.

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 three paragraphs with clear sections: action, process, security. It is front-loaded with the main purpose and maintains good structure without excessive verbosity.

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 output schema exists and the tool has two well-described parameters, the description covers purpose, behavior, and security adequately. It does not need to detail return values due to the output schema.

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%, so the description adds marginal value. It clarifies task_id origins ('from submit_sample') and repeats max_preview's default, but does not provide significant additional meaning 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?

The description states 'Download extracted memory-dump strings for a job and preview them', clearly indicating the verb and resource. It does not differentiate from sibling tools, but the purpose 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?

The description implies usage for fetching strings from memory dumps via Hybrid Analysis. It lacks explicit when-to-use or when-not-to-use guidance and does not reference alternatives among the 19 sibling tools.

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?

Discloses saves to disk, returns only metadata, format differences per backend, and security warning (untrusted data). Without annotations, it covers key behavioral traits well, though could mention if operation is safe/destructive.

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?

Four well-structured sentences, each adding value. Purpose first, then behavioral details, returns info, and security. No redundancy or waste.

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?

Covers essential aspects: purpose, behavior, format differences, security. With output schema present, return values are handled. Could mention permissions or error cases but minimal 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% with clear description for task_id. Tool description reiterates the schema's format but adds no new semantics beyond baseline.

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 states the tool downloads PCAP for finished detentions, with verb and resource. It distinguishes from sibling tools like download_sample and get_report by specifying network traffic capture and condition.

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?

Implies usage after detonation is finished and specifies task_id format, but lacks explicit guidance on when not to use or alternatives. The security warning is helpful but doesn't fully clarify usage context.

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?

No annotations exist, so description carries full burden. Discloses that hybrid_analysis returns live data while triage/malwarebazaar return documented limits, and anyrun requires paid plans. Does not mention response format or side effects, but output schema exists.

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?

Description is front-loaded with the core purpose, then breaks down per sandbox. Each sentence earns its place, though slightly verbose with bullet-like structure. Still, no fluff.

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 only one parameter with full schema coverage and an existing output schema, the description fully covers what the agent needs to know for correct invocation. No 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 covers 100% of parameter descriptions. The description further clarifies the meaning of each value and what type of data they return, adding semantic value beyond 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?

The description starts with a clear verb+resource: 'Get API quota / usage limits for one sandbox backend.' This immediately distinguishes it from sibling tools which deal with analysis, scanning, samples, etc.

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 'Use this before bulk submissions to avoid burning the user's quota.' Also details different behaviors per sandbox type, providing context for when to call. No explicit when-not or alternatives, but siblings are unrelated.

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?

With no annotations, description carries full burden. It explains polling behavior (non-blocking, exactly one status poll), possible responses, the report structure, security warning about untrusted data, and first-time caching. Very transparent.

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?

Description is detailed but well-structured with sections and bullet points. Every sentence is useful with no wasted words.

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 complexity (polling, report structure, security), description is very complete. Output schema exists but not shown, yet description describes report fields adequately.

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 100% so baseline 3. Description adds meaning: explains task_id format and that it comes from submit_sample, adding 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?

The description clearly states the tool polls a submitted detonation job and fetches the report if finished. It distinguishes from siblings like submit_sample (which returns task_id) and other analysis 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?

Explicitly says when to call (with task_id from submit_sample), what to do if still running (wait poll_after_seconds), and notes the first report may be slower. Does not explicitly say when not to use, but context is clear.

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?

With no annotations provided, the description discloses decoding behavior, file saving, return format (paths and count), and a security warning. It covers key behavioral traits but does not mention potential side effects like disk usage or error conditions.

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 four sentences, front-loaded with the main action, and each sentence adds necessary detail (encoding handling, return format, security). No waste.

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 tool's low complexity, full schema coverage, and existing output schema, the description is sufficiently complete. It covers purpose, parameter source, and key behavioral context.

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 schema already describes task_id, but the description adds 'from submit_sample,' clarifying the source and format. This adds value beyond the schema's description, which is brief.

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?

Description clearly states 'Download detonation screenshots as PNG files on disk.' The verb and resource are specific, and the tool is distinct from siblings like get_dropped_files or get_pcap.

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 usage after detonation but does not explicitly state when to use this tool versus alternatives (e.g., get_report might also contain screenshots). No when-not or alternative guidance is provided.

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?

No annotations exist, so description carries full burden. It discloses 404/working retry behavior and a security warning about untrusted data, which adds critical context for an agent.

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 concise paragraphs with no wasted words: purpose, retry guidelines, security warning. Front-loaded with the action.

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 one parameter, an output schema, and no annotations, the description fully covers the necessary context: how to use, retry, and security implications.

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?

Only one parameter scan_id with 100% schema coverage. The description adds meaning beyond schema by specifying it expects 'urlscan:<uuid>' from scan_url (also bare uuid), which helps correct invocation.

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 states it fetches a finished scan result by scan_id. The verb 'Fetch' and resource 'scan result' are specific, and it distinguishes from sibling tools like scan_url.

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 provides usage context: use after scan_url, and explains retry behavior when scan is still running (404 -> status working). It doesn't explicitly exclude alternatives but gives clear 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?

No annotations are provided, so the description carries the full burden. It discloses that the tool queries multiple external services, deduplicates results, and includes a security warning about untrusted data. This adds behavioral context beyond the name, though it doesn't specify read-only or destructive nature (likely read-only).

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 concise: three sentences plus a bullet list and a security note. The main purpose is front-loaded, and every sentence adds value without redundancy. It's well-structured and 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?

Given the tool has an output schema (not shown), the description doesn't need to explain return values. It covers input types, process (fanning across corpora, deduplication), and a security warning. For a pivot tool with multiple sources, it is fairly complete, though it could mention if results are limited or paginated.

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% with a single 'indicator' parameter described as 'the value to pivot on.' The description adds significant meaning by listing the types of indicators accepted (host, domain, URL, hash, import hash, family), which is not in the schema's description.

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 states the tool's primary action: 'Pivot an indicator to related samples and families across corpora.' It specifies the types of indicators accepted (host, domain, URL, hash, import hash, family) and lists the corpora queried, effectively differentiating it from sibling tools like search_hash or enrich_ioc.

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 explains that the tool accepts any indicator and fans it across enabled corpora, deduplicating results. While it doesn't explicitly state when not to use it or compare to alternatives, the context implies its use for multi-source pivoting, which is adequate for an agent.

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?

With no annotations provided, the description fully covers behavioral aspects: asynchronous scanning, default 'unlisted' visibility, privacy implications of public submissions, and the requirement of acknowledge_public_submission for public scans. No contradictions exist.

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 well-structured with clear sections for asynchronous behavior and privacy. It is informative without being overly verbose, though minor trimming could be possible.

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 tool's complexity (asynchronous, privacy, public flag) and the presence of an output schema, the description covers all essential aspects: submission process, retrieval method, visibility options, and the acknowledge flag 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 coverage is 100%, but the description adds valuable context for the acknowledge_public_submission parameter, explaining its role in public submissions and the current MVP behavior. The url parameter is sufficiently described in 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?

The description clearly states the tool's action ('Submit a URL to urlscan.io for live browser-based scanning') and distinguishes it from sibling tools like get_url_scan_result, which is mentioned as the retrieval counterpart.

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 explains that this tool submits a URL and returns immediately with a scan_id, and that results should be retrieved with get_url_scan_result after a delay. It explicitly contrasts submission vs. retrieval, though it does not list when not to use the tool.

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?

With no annotations, the description fully discloses: no detonation, hash validation, concurrent multi-source queries, key skipping, and a security warning about untrusted data. This covers all critical behavioral aspects.

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?

Well-organized: purpose, validation, backend details, parameter behavior, security note. Every section earns its place, though slightly verbose for the backend list format.

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 tool with output schema and good schema coverage, the description covers all necessary context: input validation, backend options, parameter behavior, and security. No 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 already describes both parameters (100% coverage). The description adds behavioral nuance for the sandbox parameter (null = all, explicit = single) and explains API key handling, providing 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?

Clear verb ('Look up') and resource ('intelligence for a file hash') with immediate differentiator ('fast, no detonation') that sets it apart from sibling tools like submit_sample or scan_url.

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?

Explains when to use (existing intel lookup), how the sandbox parameter works (null queries all, explicit queries one), and references get_report for full triage details. Could explicitly state when not to use (e.g., need detonation) but the context is clear.

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?

No annotations exist, so the description bears full disclosure. It explains query fan-out, compact match summaries, and includes a SECURITY warning about untrusted vendor data. No behavioral contradictions.

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 reasonably concise given the complexity of multiple backends, using bullet points for clarity. It is front-loaded with the main purpose, but could trim some redundancy without losing value.

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 complexity (multiple backends, varied query syntax) and the presence of an output schema, the description is highly complete. It covers security, concurrent queries, backend-specific behavior, and result nature.

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%, but the description adds significant meaning: explains how 'query' is parsed per backend, that 'limit' is a soft cap per source, and 'source' can be null or a specific backend. This goes well beyond schema defaults.

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 states the tool searches for samples/IOCs across multiple backends, with specific verbs and resources. It distinguishes from siblings like search_hash by detailing multi-backend fan-out and backend-specific query interpretation.

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?

Provides explicit guidance on using source=None for all backends vs. an explicit source for a single backend. Describes query formats per backend, enabling the agent to choose the appropriate approach.

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?

With no annotations provided, the description fully discloses key behaviors: immediate return with task_id, asynchronous detonation (2-10 min), polling via get_report, refusal without acknowledge_public_submission=true, and public data implications. This adds significant value beyond the schema.

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 front-loaded with the main purpose and structured with warnings and workflow steps. While it has multiple paragraphs, every sentence earns its place given the complexity of the tool. Could be slightly shorter but still 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?

Given 5 parameters, 100% schema coverage, output schema present, and sibling tools listed, the description is highly complete. It covers return behavior (task_id), asynchronous nature, polling, public submission handling, and limitations of backends, leaving no major 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 description coverage is 100%, so baseline is 3. The description adds meaning beyond the schema by explaining the two-step submission process (first call without ack, then with ack) and the warning about public tiers, which enriches parameter understanding.

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 states the verb 'Submit' and resource 'suspicious file or URL to a cloud detonation sandbox'. It distinguishes from siblings like search_hash (for static intel) and get_report (for polling results), making the purpose specific and 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?

The description provides explicit when-to-use guidance, including a two-step workflow for public backends, warning about public data, and alternatives like using search_hash for malwarebazaar. It also notes paid plan requirement for anyrun, giving comprehensive usage instructions.

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