Scrutica

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

Beyond the readOnlyHint annotation, the description discloses important behavioral traits: results are 'bounded summaries' with at most 24 events and truncation declared in metadata; removals are returned separately; zero-count weeks are 'a real quiet-Federal-Register signal, not missing data'; event dates are derived and labeled; and counting should use the count field, not sample lists. These add substantial context beyond the annotation.

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 long but information-dense. Every sentence contributes either purpose, usage boundaries, return structure, or counting caveats. It is front-loaded with the core purpose and usage preference. Slightly redundant details exist (e.g., 'bounded summaries' repeated), but overall it is efficiently structured for the complexity of the tool.

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 fully explains return shape: each event carries FR citation, notice metadata, counts, entity samples, and cross-references; removal actions are separate; and a last-N-ISO-week rollup is included. It also covers edge cases like zero-count weeks and truncation. This makes the description complete for an AI agent.

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 adds extra semantics: limit notes 'newest first' and that count fields report full totals; weeks references the change-log page's own window; company_id explains the id space and that entities without cross-references never appear under scope. This goes beyond schema descriptions, earning a 4.

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 opens with a specific verb+resource statement: 'What CHANGED in the BIS Entity List, as bounded change-log summaries.' It clearly distinguishes itself from the sibling scrutica_query_export_controls by stating 'PREFER this over scrutica_query_export_controls for freshness questions' and explicitly directing entity-lookup use to that sibling. This makes the purpose unmistakable.

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 and when-not-to-use guidance: 'PREFER this over scrutica_query_export_controls for freshness questions' and 'Do NOT use this to look up one entity's designation rows — use scrutica_query_export_controls.' It also explains the scoping use of company_id, giving clear conditions for that parameter.

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?

Beyond the readOnlyHint annotation, the description discloses that the result is an estimate with bounds and an is_estimated flag, and that it matches the Interactive Methodology Explorer. This adds meaningful behavioral context about uncertainty and output interpretation. It does not over-explain side effects, but for a read-only estimation tool this 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 three concise, front-loaded sentences. The first sentence states the primary action, the second names the return structure and methodology link, and the third gives a critical usage caution. Every sentence earns its place with no redundancy 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 no output schema, the description compensates by stating the return format (point estimate + bounds) and the is_estimated flag. It also references the methodology URL for deeper context. It could mention units or clarify how the precision parameter interacts with 'BF16,' but overall it provides enough context for an agent to invoke the tool and interpret results.

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 already documents 4 of 5 parameters with descriptions (80% coverage), so the baseline is 3. The tool description itself does not add detailed parameter-level semantics beyond noting 'BF16' and 'hardware configuration,' which maps loosely to the precision and hardware_type/unit_count parameters. This is sufficient but not exceptional.

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 opens with a specific verb and resource: 'Compute peak BF16 FLOP estimates for a hardware configuration.' This clearly distinguishes the tool from its siblings, which all concern entity lookups or searches. It also immediately conveys the tool's core purpose and precision focus.

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 usage context by stating the tool returns a point estimate plus bounds and points to a methodology reference. It also gives an explicit 'do not' instruction: 'Do NOT present outputs as exact measurements — always relay the bounds and the is_estimated flag.' It does not name alternative tools, but the context is sufficient given the sibling set.

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 annotation readOnlyHint=true already covers the safety profile, lowering the burden. The description adds value by enumerating return fields (legal name, country of HQ, organization type, parent/subsidiary references, supply-chain edge counts) and clarifying that full edge graphs are not included. It does not mention error handling or rate limits, but for a simple read-only getter this is not a significant gap.

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: the primary action first, a return-value list second, and two 'use instead' directives at the end. Every sentence adds value with no redundancy or fluff, making it highly concise and well-structured.

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 a single well-documented parameter and no output schema, the description adequately covers what the tool returns and how to obtain the required ID. It also guides the agent to sibling tools for related queries, making selection and invocation unambiguous in typical workflows.

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% — the only parameter (company_id) has a detailed description with format, examples, and resolution guidance. The tool description only repeats 'canonical Scrutica ID' without adding new parameter-level semantics. Baseline 3 is appropriate because the schema carries the full burden.

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 'Fetch complete details for a single organization by canonical Scrutica ID' with a specific verb and resource. It also distinguishes from siblings by directing to scrutica_query_export_controls for BIS details and scrutica_get_supply_chain for full edge graphs.

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?

It explicitly says to use scrutica_query_export_controls for BIS designation details and scrutica_get_supply_chain for full edge graphs, providing clear alternatives. The schema description further instructs to resolve IDs via scrutica_search first, which is a concrete prerequisite.

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. The description adds meaningful behavioral context: it returns is_estimated flags and data-quality flags, warns not to guess slugs, and explains the limitation regarding BIS exposure. This goes beyond the annotation and provides useful operational detail.

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 moderately long but every sentence earns its place: purpose, return fields, cross-tool guidance, and explicit exclusions. It is front-loaded with the main action and then provides necessary supporting details 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?

Without an output schema, the description compensates fully by enumerating the return fields (operator, owner, country, capacity, GPU inventory, etc.). It also covers prerequisites (resolve ID), limitations (no BIS chain), and related tools, making it contextually complete for a simple read operation.

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 parameter description is already rich, specifying format ('fac-<slug>'), concrete examples, and explicit instructions to resolve via scrutica_search. The tool description reinforces this but doesn't add new semantic meaning; however the combined clarity justifies above-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 fetches complete details for a single Scrutica facility by canonical ID, using a specific verb and resource. It distinctly separates this from sibling tools by noting it does not compute BIS exposure and that facility IDs must come from scrutica_search.

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?

Explicit guidance is provided: resolve facility IDs via scrutica_search first, and use scrutica_query_export_controls for BIS Entity List designations. It also explicitly states what this tool does NOT do (ownership-chain BIS exposure), making the usage boundary completely 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?

ReadOnlyHint is true, and the description adds valuable detail about the return shape (canonical URL + section anchor + summary). This exceeds the annotation's simple safety signal, though it doesn't describe edge cases or additional 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?

The description is compact and front-loaded: purpose in the first sentence, topics in the second, and return/usage in the third. No filler words, and every sentence adds distinct 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?

For a one-parameter tool with a clear enum and a read-only action, the description covers purpose, usage trigger, topic list, and return format. Even without an output schema, the agent knows what to expect. It is complete for the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It does by listing all enum values in prose and explaining that the topic refers to a 'metric or index,' which adds context beyond the bare enum. Given the single parameter's simplicity, this is sufficient.

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 opens with a specific verb+resource: 'Return methodology documentation for a Scrutica metric or index.' It clearly distinguishes this from sibling tools focused on entities, scenarios, or searches. The explicit list of topics further clarifies 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?

The description provides an explicit when-to-use instruction: 'Use this when a user asks "how did you calculate X".' However, it does not mention when not to use it or name alternative tools, so it falls short of a full 5.

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?

While annotations already declare readOnlyHint=true, the description adds substantial behavioral context: returns summary plus serialized substrate with per-item sources and authority tiers, notes capped lists shipping true totals, and explicitly states the propagation simulation is interactive-only. This goes well beyond the annotation.

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 well-structured sentences: purpose, available values with inline explanations, and return behavior. Every sentence adds necessary information, and the critical limitations are front-loaded in the final sentence.

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 fully covers what the tool returns (summary + substrate), what it does not return (simulation), and the capping behavior. The single parameter is completely explained via the listed scenario IDs, making the tool self-contained.

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 provides only an enum of scenario_id values with zero descriptions. The description compensates by explaining each value (e.g., 'taiwan-strait (4 TSMC disruption scenarios)'), giving the agent full semantic understanding of the only parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Fetch geopolitical compute risk scenarios.' It then lists the available scenarios with their unique contents, which clearly distinguishes this tool from sibling get_* tools for companies, facilities, supply chains, 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?

The description provides clear context that this tool is for risk scenarios, but it does not explicitly name alternative tools or state when not to use it. The sibling tool names imply the domain, yet the guidance is not fully explicit.

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?

Beyond the readOnlyHint annotation, the description discloses significant behavioral nuances: announced_usd is not comparable across countries, reality_ratio measures disclosure rather than execution, and reality_ratio is null for many programs due to unpublished disbursed figures. It also explains the denominator logic and why nulls concentrate in certain countries, adding essential interpretive 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 front-loaded with the core action and return fields, followed by clearly separated caveats. Every sentence carries meaningful information, and the structure prioritizes the critical warnings about field comparability. Though lengthy, it is appropriately sized for the tool's conceptual complexity.

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?

This is a read-only data tool with no output schema; the description compensates by enumerating the returned fields and explaining each caveat in detail. It also covers all three parameters, including edge cases like regional programs and list_all behavior. For the tool's complexity, the description is complete and actionable.

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 already describes all three parameters, so the baseline is 3. The description adds valuable nuance: the bare country_code is accepted for program_id, regional programs require program_id, and list_all returns a summary table. This extra guidance improves parameter understanding 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 'Fetch detailed data on a national sovereign AI compute program' — a specific verb and resource, and it enumerates the returned fields. This clearly distinguishes it from sibling tools focused on companies, facilities, or scenarios. The purpose is unambiguous and informative.

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 name alternatives or explicitly state when not to use this tool. It does provide context for when to use program_id vs. country and what list_all does, which is helpful but not a full usage guide. Sibling comparisons are absent.

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, covering the safety profile. The description adds valuable behavioral context about data sources (licensed database, SEC Exhibit 21), snapshot date, and the guarantee that data is not redistributed, going beyond annotation basics.

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 sentences, front-loaded with purpose, then parameter semantics, then output and dataset context. Every sentence earns its place with no redundancy or 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 there is no output schema, the description compensates by listing the edge fields (source_org_id, target_org_id, relationship_type, supply_share, price_correlation_3m, data_source). It also provides dataset size and provenance, making the tool's behavior fairly complete. Minor gaps include lack of pagination or limit usage details, but the core use case is well covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%, with only org_ids having a description. The description compensates by thoroughly explaining the 'direction' parameter (upstream/downstream/both) and implicitly clarifying that org_ids refer to Scrutica org IDs. The 'limit' parameter remains undocumented in both schema and description, but its numeric nature limits the gap.

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 returns supply-chain relationships for organizations, using specific verbs and resources. It distinguishes itself from siblings like get_company and get_facility by focusing on edges rather than single entities.

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 explicitly explains the 'direction' parameter with upstream/downstream semantics, giving clear context for when each option is appropriate. However, it does not explicitly name alternative tools or state when not to use this tool, so it falls short of a perfect score.

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?

Beyond the readOnlyHint annotation, the description discloses the authority tier (Tier 1), the two coverage classes (explicitly_named vs affiliate_50pct_rule), the conditional presence of coverage_note, and the load-bearing nature of data_quality_flags. This rich context tells the agent exactly what the data means and how to interpret edge cases.

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 dense yet efficiently organized: it leads with the core purpose, then exclusions, then matching semantics, then return fields, then data-quality caveats. Every sentence carries unique information, and no word is wasted. The length is justified by the tool's complexity.

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 tool has no output schema, so the description must explain return values—and it does, listing all key fields and the semantics of data_quality_flags. It also covers authority tier, coverage classes, and caveats, giving an agent everything needed to correctly interpret results. No obvious 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?

The description adds important nuance to entity_name (case-insensitive substring, no alias expansion) and explains the output fields, but it directly contradicts the input schema, which states entity_name is 'fuzzy matched against aliases'. This creates a confusing conflict for an agent deciding how to pass the parameter. With 75% schema coverage, the description should clarify—not contradict—and the mismatch undermines the added value.

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 opens with a specific verb and resource: 'Look up BIS Entity List designations for companies or countries.' It further distinguishes the tool from OFAC SDN and Wassenaar CCL, and explicitly names the sibling tool scrutica_get_company for OFAC status, making its scope unmistakable.

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 clearly states what the tool covers (BIS Entity List, Federal-Register-anchored) and what it does not cover (OFAC SDN, Wassenaar CCL), and directs users to scrutica_get_company for OFAC-related queries. It also documents the entity_name matching behavior (case-insensitive substring, no alias expansion), which is essential for correct use.

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, so the safety profile is known. The description adds context about search scope (facilities/companies/sovereign programs), return format (ranked results with id/name/type/summary/URL), and explicit exclusions, which go beyond the annotation but don't cover rate limits or pagination.

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 sentences, all substantive: purpose, return type, filters, and exclusions. Front-loaded with the main action, no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a search tool with no output schema, the description covers purpose, return fields, filters, and exclusions well. It lacks pagination/limit behavior details, but the schema covers limits, and the exclusions make it quite complete for selection.

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 75% of parameters with descriptions (query, country, entity_type). The description reinforces the filtering semantics ('Filter by entity_type', 'Filter by ISO 3166-1 alpha-2 country code') but adds no new details beyond schema, and limit remains undocumented in both.

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 'Search facilities, companies, or sovereign programs by free-text query' with a specific verb and resource scope. It also lists return fields and explicitly distinguishes from sibling tools like scrutica_get_company and scrutica_query_export_controls.

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 when-to-use context ('by free-text query') and clear when-not-to-use with named alternatives: 'Do NOT use this for BIS Entity List / export-control lookups — use scrutica_query_export_controls' and 'Do NOT use this for supply-chain traversal — resolve an entity ID first via this tool, then call scrutica_get_supply_chain'.

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