ampel

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

With no annotations provided, the description carries the burden of disclosing behavior. It does explain that the tool returns status conditions (GREEN/YELLOW/RED) and evidence, which gives some insight into output. However, it does not explicitly state that it is a read-only operation, whether it queries live data, or any side effects 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 a single, front-loaded sentence that states the core purpose ('Detailed Ampel') and key features (conditions with evidence). It is concise and free of fluff, though a slightly more structured breakdown could improve scannability.

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 no output schema and no annotations, the description should more fully explain what the returned report contains and any usage context. It mentions evidence and conditions but does not clarify the number of checks, how evidence is presented, or whether the tool computes results on demand. It is minimally complete for a simple status tool but leaves gaps for an agent deciding to invoke it.

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 the parameters 'article' and 'entity_id' are already documented. The description does not add additional meaning beyond confirming the tool is for a specific DORA article, which aligns with the 'article' parameter. Per rubric, baseline 3 is appropriate when schema covers all parameters.

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

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

The description clearly identifies the tool as providing a detailed traffic-light status ('Ampel') for a specific DORA article, with conditions and evidence. It distinguishes itself from broad assessments like 'assess_all' by specifying it is for a single article, but it does not explicitly name alternatives or contrast with 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 does not provide any guidance on when to use this tool versus alternatives. It simply describes the output without indicating prerequisites, exclusions, or preferred contexts. No mention of when to choose 'article_status' over 'evidence_summary' or 'gap_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?

With no annotations provided, the description carries the full burden for behavioral disclosure. It states that the tool re-runs a full assessment and recomputes statuses, implying a write or mutation operation, but it does not disclose whether results are overwritten, whether permissions are needed, or any side effects.

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 two short sentences and entirely front-loaded with the primary action. Every word adds value, and there is no redundant or extraneous 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 tool with one optional parameter and no output schema, the description is minimally adequate: it names the action and the evidence used. However, it omits what the return value or status update looks like, and the lack of annotations makes the side effects unclear.

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% for the single optional parameter, entity_id, which has a clear description. The tool description adds no additional meaning beyond what the schema already provides, so a 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 uses specific verb+resource: "Re-run full assessment for an entity" and clarifies the outcome with "Recomputes Ampel statuses from all available evidence." This distinguishes it from sibling tools like retest_finding or run_trial_assessment by indicating a comprehensive, all-evidence reassessment.

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 usage guidance is provided. The description does not state when to choose this tool over alternatives like cross_oracle_assess or retest_finding, nor does it mention any preconditions or 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only adds 'chain-linked' and 'integrity check', which hints at verification behavior but does not state whether the operation is read-only, what happens on integrity failure, or what the return format is. This is insufficient for an agent to predict the tool's side effects 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 extremely short (six words), which is concise and front-loaded, but it is more under-specified than effective. It omits a verb and critical behavioral context, so while it is not verbose, it fails to provide enough substance to be a genuinely useful tool description.

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 absence of annotations, output schema, and required parameters, the description is the sole source of context. It does not explain return values, pagination, error behavior, or the role of 'entity_id'. For a tool with two parameters and no output schema, this level of detail is inadequate for an agent to use it correctly without external knowledge.

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 describes 'limit' with 'Max entries', but 'entity_id' has no description, leaving its purpose ambiguous (likely a filter, but unstated). The tool description itself adds no parameter information, so the semantics of half the parameters are entirely unexplained. At 50% schema coverage, the description should compensate for the undocumented parameter, but it does not.

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 'Chain-linked audit log with integrity check' identifies the resource (audit log) and a notable property (chain-linked integrity), but lacks a verb or explicit action such as 'retrieve' or 'verify'. It is more of a noun phrase than a tool purpose statement, and while it distinguishes from many sibling tools by focusing on audit trail, it does not clearly state what the tool does.

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 no guidance on when to use this tool versus alternative audit/log-related siblings like 'evidence_pack' or 'evidence_summary'. There are no use-case examples, exclusions, or comparisons, leaving the agent to infer appropriate usage from the name alone.

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 must carry the burden of behavioral disclosure. It discloses the 'Live' nature (real-time API call) and the config requirement (setup/auth context). However, it does not explicitly state read-only behavior, potential side effects, or any rate limits. This is a partial disclosure, hence a 3.

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 only two sentences, front-loaded with the core function, and every phrase adds value (data points, regulatory purpose, config prerequisite). No fluff 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?

For a simple tool with one parameter and no output schema, the description is quite complete: it lists the data retrieved, the regulatory context (DORA Art. 9), and the setup requirement. It could be slightly more explicit about the exact return format, but the listed data points largely cover that. A 4 is appropriate.

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% for the single parameter (force_refresh), which the schema already describes as 'Force fresh API call (default true)'. The description adds no parameter-specific meaning, so the 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?

The description clearly specifies what the tool does: it checks Azure AD integration and lists concrete data points (MFA registration %, risky users, conditional access policies). This distinguishes it from sibling tools focused on contracts, reports, and assessments. The verb is implied by the tool name 'azure_ad_check' and reinforced by 'Live integration'.

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 usage context: 'DORA Art. 9 evidence' tells when this tool should be used, and the config requirement gives a prerequisite. However, it does not explicitly mention when not to use it or point to alternative tools, so it's clear but not fully differentiated.

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 mentions 'Creates signed approval evidence,' indicating a write operation, but does not disclose whether the report is actually sent, what side effects occur, or any prerequisites. The behavior is under-specified for a mutation tool.

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 very concise, with two short clauses that both contribute to the core purpose. It is appropriately front-loaded, though it is perhaps too terse for the tool's complexity, which lowers it slightly from a perfect score.

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 four parameters, no output schema, and no annotations, the description is insufficient. It does not explain the approval workflow, what 'signed approval evidence' entails, or any consequences of approval. The tool's context in the broader BaFin reporting process is only hinted at via the 4-eyes principle.

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 four parameters with 0% description coverage, and the description adds no meaning to entity_id, report_id, approver_name, or approver_role. While some are inferable from names, the description fails to clarify required or optional usage, especially since no parameters are marked required.

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 approves a BaFin report for submission using a 4-eyes principle, with a specific verb ('Approve') and resource ('BaFin report'). It does not explicitly contrast with sibling tools like bafin_report_draft, but the resource and action disambiguate it from other approval 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 '4-eyes principle' provides clear context that this tool is part of a two-step approval workflow, implying use after drafting and before submission. It does not explicitly state when not to use it or name alternatives, but the context is sufficiently 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, the description partially carries the behavioral disclosure burden. It explicitly states 'Preview mode' and 'requires board approval', which clarifies that it does not send the report and needs workflow approval. However, it does not mention side effects, persistence, authentication needs, or error behavior, leaving important gaps.

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 very concise: two short sentences, with the main action front-loaded. Every word adds value, and there is no repetition of schema details.

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 10 parameters, no output schema, and no annotations, the description is insufficiently complete. It does not state what the tool returns (e.g., a draft document or status), whether it persists data, or how to handle required fields. The 'Preview mode' hint helps but is not enough to make the tool's behavior clear.

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 only 20% (2 of 10 parameters have descriptions). The tool description does not explain individual parameters; 'All mandatory fields per DORA Art. 19/20' is a compliance statement but adds little about parameter meanings like title, entity_id, or remediation. This does not compensate for the poor 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's function: 'Generate ITS 2024/1772 compliant BaFin incident report draft.' It names a specific verb ('generate'), a specific resource ('BaFin incident report draft'), and regulatory context ('ITS 2024/1772'). This distinguishes it from siblings like 'bafin_approve_send' and generic 'generate_report'.

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 'Preview mode — requires board approval' provides clear context that this tool produces a draft that must be approved before submission, implying it is not for final sending. However, it does not explicitly name alternative tools or state when not to use it, so it stops 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?

With no annotations, the description carries the full burden. It lists the summary contents but doesn't disclose whether the tool is read-only, if it requires specific permissions, how fresh the data is, or any side effects. It provides minimal behavioral insight beyond its purpose.

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, front-loaded with the key term 'Executive board summary', and no redundant information. Every word contributes.

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 lists the summary's contents but doesn't specify return format, whether entity_id is required, or what happens if it's missing. Since there's no output schema, more detail about the response would improve completeness.

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 parameter entity_id is fully described. The description adds no further meaning to the parameter, but the schema already handles it adequately.

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 provides an executive board summary with specific components (overall score, top 5 risks, etc.). It distinguishes from siblings like evidence_summary by orienting to management/board reporting, though it doesn't explicitly name alternatives.

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 'Designed for management/board reporting' gives clear context for when to use it. However, there is no explicit exclusion or mention of alternatives, so it doesn't fully meet the 'when-not' 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?

No annotations are provided, so the description carries the burden. It clearly discloses the side effects of approval: signed evidence, Ampel upgrade, audit log. However, it does not disclose what happens on rejection (e.g., audit logging, state change), leaving a gap for half the tool's functionality.

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 sentence with a clear opening verb and outcomes. No filler or repetition, and the most important information is front-loaded.

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 explains the approval side well but omits rejection behavior and return value. With no output schema and no annotations, the tool is only partially specified. The lack of required parameters hints at conditional logic that is not addressed.

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 provides 100% coverage with descriptions for all four parameters. The description adds extra context about the approval process but does not clarify parameter relationships (e.g., when rejection_reason is required). This matches the baseline for full 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's purpose: 'Approve or reject a bridge resolution.' It also names concrete outcomes (creates signed evidence, upgrades Ampel to GREEN, logs to audit chain), which distinguishes it from bridge_resolve and bridge_status.

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 context is clear: this tool is for acting on a bridge resolution. It does not explicitly state when not to use it or mention alternatives, but the verb 'approve/reject' makes its role distinct. No exclusions are given, so it does not fully meet the 'explicit when/when-not' bar.

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 responsibility for behavioral disclosure. It describes the output classification but does not explicitly state whether this is a read-only operation, any side effects, or required permissions. The 'report' name implies safety, but that is implicit rather than explicit.

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 introduces the main purpose without any fluff or redundancy. It efficiently conveys the classification categories and additional output fields.

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 is simple with one optional parameter and no output schema. The description explains the gap classification dimensions but does not detail the exact report structure, return format, or how entity_id affects the output. This is adequate for a basic report tool but leaves some 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 a single optional entity_id parameter that has a description. The tool description adds no additional meaning beyond what the schema already provides, so the baseline score 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 clearly states the tool classifies gaps into DATA/EVIDENCE/POLICY/WORKFLOW categories and provides closure path, owner, and effort level. This distinguishes it from sibling tools like gap_report by specifying a unique classification scheme, though it does not explicitly name alternatives.

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 guidance is given on when to use this tool versus alternatives like gap_report or assess_all. The description implies usage for gap analysis but offers no explicit context, prerequisites, or 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?

No annotations are present, so the description carries the transparency burden. It discloses useful behavioral traits: generates templates and tracks the approval process. However, it omits details about persistence, side effects, required permissions, idempotency, or behavior on repeated calls, leaving some ambiguity for a state-changing workflow starter.

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 with no filler. The key action, generated artifacts, tracking behavior, and follow-up tool are all packed efficiently. The description is front-loaded and every sentence 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 workflow starter with a well-documented input schema, the description is fairly complete: it names the workflow, lists the templates, mentions approval tracking, and directs to the next tool. It lacks return/result details, but no output schema exists and the follow-up step is explicitly indicated, making the overall context sufficient.

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 the baseline is 3 even if the description adds no parameter details. The description does not mention parameters, but the schema already documents check_id, entity_id, and expiry_days with sufficient meaning. No extra semantics are needed.

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

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

The description uses the specific verb 'Start' with the resource 'bridge resolution workflow' and enumerates generated templates (Risk Acceptance, Contract Renegotiation, Concentration Policy, Exit Strategy), clearly distinguishing it from siblings like bridge_approve and bridge_status. This makes the tool's role in the pipeline 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?

It clearly states the action ('Start bridge resolution workflow') and provides sequencing guidance by directing the agent to call bridge_approve for sign-off. It does not explicitly describe when not to use this tool or name alternative starting points, but the context is clear enough for an agent to proceed.

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 burden. 'Check' implies a read-only operation, which is safe, and the description lists the statuses shown. However, it does not explicitly state it does not modify data or disclose any limitations or prerequisites beyond what schema already provides. It adds moderate context but not deep behavioral 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?

Two concise sentences, front-loaded with verb and resource, no filler. Every word adds 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?

For a simple status tool with one optional parameter and no output schema, the description provides the purpose, scope, and expected statuses. It is sufficient for invocation, though it lacks explicit return format details, which are not expected for such a 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 coverage is 100% with entity_id described as optional. Description only adds 'for an entity,' which does not add meaningful semantics beyond the schema. Baseline 3 applies since schema covers all parameters.

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 uses specific verb 'check' with resource 'all bridge resolution workflows for an entity' and enumerates output states (open, pending, closed, rejected). This clearly differentiates from sibling action tools like bridge_resolve and bridge_approve.

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 guidance on when to use this tool versus alternatives. There is no mention of use cases, exclusions, or comparison to bridge_report or other status tools. Usage is only implied by the purpose.

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 description hints at the scope (events, cross-refs, connected oracles) but does not disclose behavioral traits such as read-only nature, side effects, or how the entity_id parameter affects the result. With no annotations, the agent is left to infer safety and 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 extremely concise and front-loaded, using a telegraphic style with no wasted words. It is appropriately sized for a simple tool, though slightly cryptic in its brevity.

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 low-complexity tool with one optional parameter and no output schema, the description still leaves out return values and usage context. It does not explain what 'status' returns or how to use entity_id, making it incomplete for an agent to select and invoke correctly.

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

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

The input schema provides a complete description for entity_id ('Entity ID for cross-refs'), so the parameter semantics are adequately covered. The tool description itself adds no additional meaning beyond what the schema already provides.

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 identifies the tool as a status reporter for Oracle Event Bus, specifically covering events, cross-refs, and connected oracles. This distinguishes it from other status tools by naming the specific resource, though it lacks an explicit verb like 'get' or '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?

No usage guidance is provided. It does not indicate when to prefer this over sibling status tools such as bridge_status or cross_oracle_assess, nor any prerequisites or context for using the entity_id.

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 must carry the transparency burden. It discloses the return classification (PASS/WARN/BLOCK, missing clauses, bridge classification), which is valuable behavioral info. However, it does not state whether the operation is read-only, requires permissions, or has side effects, leaving some gaps in the safety profile.

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 one succinct sentence that front-loads the primary purpose and follows with the output summary. It contains no filler, making it highly 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?

The description provides a concise overview and the schema covers parameters, but the absence of annotations and output schema leaves ambiguity around the 'bridge classification' and the tool's role in broader workflows. It is adequate but not fully self-sufficient for a 6-parameter 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 83%, so the schema already documents most parameters. The description adds no parameter-level detail beyond what is in the schema, meeting the baseline but not enhancing it. Given the high coverage, a 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's specific action: 'Check DORA Art. 30 contract clauses for a provider' and defines the scope with the regulation article and target entity. It also mentions the output format (PASS/WARN/BLOCK with missing clauses and bridge classification), which distinguishes it from generic contract tools like contract_analyze.

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 a clear context for use: DORA Art. 30 compliance checking. It implies the appropriate scenario without naming alternatives or exclusions. A 5 would require explicit when/when-not guidance, but the specificity of the regulation article makes the usage context quite 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 carries the full burden of behavioral disclosure. It states 'Collect' and 'Auto-assesses' but does not clarify whether this is a read-only operation, what 'auto-assesses' entails, whether it persists data, what side effects occur, or any authentication/rate-limit constraints. This is a significant gap for a tool that could have mutation implications.

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 two terse sentences, front-loaded with the primary verb and resource, and every word earns its place. It is concise without being under-specified for the purpose it serves.

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 and no annotations, yet the description does not explain the return format or what 'auto-assesses' produces. The single optional parameter is covered, but the overall context of what the agent receives after invocation is missing. Given the simple parameter set, more clarity on output and assessment behavior is expected.

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% for the single optional parameter entity_id, which the schema describes as 'Entity ID (optional)'. The description adds no additional meaning to this parameter beyond the schema. Baseline of 3 is appropriate since the schema already provides sufficient 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?

The description clearly states a specific verb ('Collect') and resource ('live Art. 10 evidence') from named sources (NVD, CISA KEV, CERT-Bund), and adds the distinct 'Auto-assesses' behavior. This distinguishes it from sibling tools like evidence_pack or freshness_check, which focus on packaging or checking rather than live collection from these specific 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?

The description gives no explicit guidance on when to use this tool versus alternatives. It implies usage when fresh evidence is needed, but there is no mention of exclusions, prerequisites, or references to sibling tools. The absence of any 'when to use' context leaves the agent without clear decision support.

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 full burden. It discloses the analysis scope and enumerates output fields (compliance status, confidence score, extracted text, gap reasoning, suggested fix), providing a transparent view of behavior. It does not mention side effects, but for this read-like analysis tool the output disclosure is substantial.

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 two sentences: the first names the action and scope, the second enumerates the output. It is concise, front-loaded, and contains 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 single-parameter analysis tool with no output schema, the description covers input source (via schema), action, clause detail, and return fields. It lacks explicit prerequisites about contract state, but enough context is present for an agent to use it correctly.

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

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

Schema description coverage is 100% ('document_id' described as 'Document ID from contract_upload'). The description adds no additional parameter semantics, but the schema already fully explains the single parameter, so the 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 uses a specific verb ('Analyze') and resource ('contract against 15 DORA Art. 30 mandatory clauses'), and clearly distinguishes from siblings like 'contract_status' or 'check_contract' by specifying the exact clause scope and output components.

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 contract_upload by referencing document_id, and clearly sets the context of analyzing against DORA Art. 30. It does not explicitly mention alternatives or exclusions, but the context is clear enough for correct selection.

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?

There are no annotations, so the description must disclose behavioral traits. It partially does by indicating it's an overview/read operation, but it does not state permissions, data scope limitations, or response format. Since it's not explicitly readonly and no safety annotations exist, the disclosure is insufficient.

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 sentence front-loaded with the primary purpose, containing no fluff. It efficiently conveys the essential information in ~12 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?

Despite the tool being relatively simple, the description does not mention that entity_id is optional (no required parameters), nor does it describe output format or any limitations. This ambiguity is significant for an agent trying to invoke the tool correctly.

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

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

The schema already documents entity_id with a description, providing 100% coverage. The description adds only 'per entity' which aligns with the parameter but does not clarify whether the parameter is required or how it affects results given that no parameters are marked required.

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 uses a specific verb 'Shows' and identifies the resource 'analyzed contracts per entity', clearly distinguishing it from sibling status tools like article_status or bus_status. It also specifies the data fields (clause gaps, review status, document versions), making the purpose 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 no guidance on when to use this tool versus alternatives. It does not mention exclusions, prerequisites, or more suitable sibling tools for related queries, leaving the agent to infer usage 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?

With no annotations available, the description carries the full burden of behavioral disclosure. It does disclose important behaviors: creating a document record with a SHA-256 hash, version tracking, and an audit trail. However, it does not mention prerequisites (e.g., entity must exist), potential side effects (e.g., overwrite behavior), or authentication/authorization needs, leaving significant gaps.

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 extremely concise and well-structured: two sentences that first state the primary action and then detail the resulting record traits. Every word adds value, with no fluff 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?

Given the tool's complexity (5 parameters, no output schema, no annotations), the description is incomplete. It does not explain the return value or next steps after upload (e.g., whether an ID is returned, or that the document can be analyzed with contract_analyze). Since there is no output schema, the description should have compensated by outlining expected outcomes.

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% parameter description coverage, so the baseline is 3. The description adds no additional parameter-level meaning beyond what the schema already provides; it does not explain relationships between parameters or clarify unusual aspects (e.g., all parameters are optional despite upload requiring some context).

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 specific action (upload contract text), the resource (contract text for DORA Art. 30 analysis), and the resulting side effects (creates document record with SHA-256 hash, version tracking, audit trail). This distinguishes it from sibling tools like contract_analyze or contract_status, which have different purposes.

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 by specifying that the upload is for DORA Art. 30 analysis, implying this tool is for ingesting new contracts rather than analyzing or checking existing ones. However, it does not explicitly mention when not to use it or name alternative tools, so it stops short of full 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 of disclosing behavioral traits. It merely says 'register' without explaining permission requirements, idempotency, duplicate handling, or return values. This is a significant gap for a creation tool.

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 sentence with no redundancy or fluff. It is appropriately sized for the minimal information it conveys, earning full marks for conciseness.

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 4 parameters, no annotations, no output schema, and no usage guidance, the description is woefully incomplete. An agent cannot infer what the tool returns, what input is mandatory, or how it differs from related tools, leaving major gaps in 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?

Schema description coverage is 50% (lei and jurisdiction lack descriptions), and the tool description does not compensate by explaining any parameters. The description adds no parameter semantics beyond the schema, and required fields remain ambiguous since all parameters are optional.

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 'Register a new regulated entity' clearly states the verb (register) and resource (new regulated entity), making the tool's purpose obvious. However, it does not differentiate from similar sibling tools like 'onboard_entity' or 'register_provider', so it misses the top score.

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 versus alternatives such as `onboard_entity` or `register_provider`. The description provides no context, prerequisites, or exclusions, leaving the agent without direction on tool selection.

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 the burden of disclosing behavior. It reveals the 48-hour expiry and no-login requirement, which are useful. However, it does not disclose what happens after expiry, whether the trial is reversible, or any side effects, leaving gaps for a creation tool.

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 two sentences with no wasted words. It front-loads the verb 'Create', then provides the key qualifiers (temporary, 48h, self-service, no login). Every part adds value and the structure is immediately scannable.

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 simple create tool with four schema-documented parameters and no required fields, the description is largely complete. It covers the tool's purpose and main constraint (48h) but lacks explicit mention of return value or post-creation behavior, which would be useful given no 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?

The input schema covers 100% of parameters with descriptions (providers, entity_name, entity_type, jurisdiction), so the schema already provides meaning. The description adds no parameter-specific information, but the high schema coverage means 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 clearly states the tool creates a temporary trial entity for self-service DORA assessment, with a 48-hour lifespan. It distinguishes itself from sibling tools like create_entity by emphasizing 'temporary' and 'trial' and 'No login needed', making its specific purpose obvious.

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 for when to use: self-service DORA assessments requiring no authentication. It implies this is for quick trials rather than permanent setups, but does not explicitly name alternatives like create_entity or state when not to use, so it lacks explicit 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?

The description discloses that the tool 'Auto-stores evidence and updates Ampel status,' which is a useful side-effect trait. However, with no annotations, the description carries the full burden and does not mention return values, idempotency, permissions, or whether it is synchronous, leaving several behavioral aspects opaque.

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, front-loaded with the core purpose, and contains no unnecessary words. The enumeration of oracles and regulations is dense but essential to convey the cross-oracle nature, though the first sentence is a fragment.

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 complex tool spanning six systems, the description is incomplete. It lacks an explanation of return values, what constitutes a check ID, how entity_id affects execution, and whether the operation is synchronous. No output schema or annotations compensate, leaving substantial gaps for correct invocation.

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% for both parameters, so the baseline is 3. The description adds little beyond listing the oracles; it does not explain valid check IDs or the exact role of entity_id in the assessment, but the schema descriptions are already clear.

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 that the tool runs 18 checks across six named oracles with specific regulations, making its purpose and scope evident. It uses a specific verb ('runs') and resource ('cross-oracle assessment'), but it does not explicitly contrast with sibling tools like assess_all or cross_regulation_check, so differentiation is implicit.

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 guidance is provided on when to use this tool versus alternatives. The phrase 'Enterprise cross-oracle assessment' implies a broad cross-oracle scenario, but there are no exclusions, prerequisites, or alternative tool mentions, leaving the agent without actionable selection 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 carries the full burden for behavioral disclosure. It says 'Tag findings' which implies a mutation or write operation, but does not disclose whether changes are persistent, if permissions are required, or if it is reversible. The second sentence describes output, but side effects are unaddressed.

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 two sentences, with the first stating the primary action and the second adding specific regulatory context. There is no redundant phrasing, and the structure is front-loaded with the core purpose.

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

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

The tool appears to be a write-operation ('Tag findings') but lacks any details about side effects, return values, prerequisites, or whether tags are visual indicators or persisted changes. Given the lack of annotations and output schema, the description alone is not sufficient for an agent to understand the full implications of invocation.

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% (one parameter 'entity_id' documented in the schema), so the description does not need to add parameter details. However, the schema's description 'Entity ID' is vague, and the tool description never clarifies what entity_id refers to (e.g., a finding ID, an entity, or a trial), leaving semantic ambiguity.

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 specifies a clear action ('Tag findings') with a distinct resource and scope (cross-regulation impact across DORA, MiCA, and AMLR). It explicitly states what the tool does and highlights a unique capability (mapping DORA findings to MiCA and AMLR), effectively distinguishing it from sibling tools like regulation_impact.

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: use this tool when needing to tag or identify cross-regulation impacts among DORA findings. However, it does not explicitly mention when not to use it or compare with alternatives such as regulation_impact or cross_oracle_assess, so it lacks exclusions but is still clear enough.

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 the full burden. It discloses a key side effect (auto-creating findings for critical matches) and references DORA Art. 10, but does not explain what happens to non-critical matches, whether existing findings are modified, or any permission/reversibility aspects. It provides some behavioral context but lacks depth.

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 extremely concise, with three short sentences: purpose, side-effect, and regulatory context. It is front-loaded with the main purpose and contains no fluff. Every sentence 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?

The tool has 3 parameters, no output schema, and no annotations. The description is too brief to cover important contextual aspects: it does not explain the meaning of DORA Art. 10 in this context, what 'critical matches' means, what the output format is, whether the operation is reversible, or how entity_id relates to the mapping. Given the side effects, this is a significant 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 67% (cve_id and vendor have descriptions, entity_id does not). The tool description adds no parameter meaning beyond the schema; it does not clarify what entity_id represents or how the three parameters interact. The schema descriptions themselves are minimal, so the agent gets little help in using parameters correctly.

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 function with a specific verb ('Map') and resource ('CVE/vulnerability to internal ICT providers and systems'), and adds a distinct side-effect ('Auto-creates findings for critical matches'). It differentiates from sibling tools by focusing on CVE-to-asset mapping with automatic finding creation, which is unique among the listed siblings.

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 when one needs to map CVEs to internal providers/systems, especially for DORA Art. 10 compliance, but does not explicitly state when to use this tool over alternatives or provide exclusions. No sibling tools are mentioned, so guidance is only implied.

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 must disclose behavioral traits. It only states what the graph includes, but does not explain whether this is a read-only operation, how data is sourced, or whether any side effects or performance implications exist. The word 'full' suggests it may be resource-intensive, but this is not clarified.

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 efficiently communicates the core purpose. It lists key elements without unnecessary elaboration, 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 no output schema and no annotations, the description should explain what the returned graph looks like, how to interpret it, and how the optional entity_id affects results. The description is too vague about the tool's behavior and output format, leaving gaps for an 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?

The schema has one parameter, entity_id, with a description 'Entity ID', giving 100% coverage. The tool description adds no further parameter semantics, but the schema already documents it adequately. The optional nature (0 required) is implied but not explicitly described.

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

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

The description clearly identifies the tool's output as a full provider dependency graph and enumerates its contents (providers, systems, checks, blast radius, SPOF detection). This is specific enough to distinguish it from sibling tools, though it lacks an explicit verb like 'generate' or 'return'.

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 gives no guidance on when to use this tool versus alternatives, no mention of prerequisites, and no exclusions. It does not say if it should be used for a single entity or all providers, leaving the agent to infer appropriate usage.

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 the full burden of behavioral disclosure. It only says 'list all' without explicitly noting that this is a read-only operation, what the return format looks like, or whether the result could be very large. This leaves the agent guessing about important 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?

The description is a single sentence that conveys the essential information without any waste. It is concise and front-loaded, with every word contributing to the 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?

For a simple list tool with no parameters and no output schema, the description provides the core action but omits important context like the structure of the returned data, potential limitations, or any relationship to other entity-related tools. It is minimally viable but leaves gaps for the 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?

The tool has zero parameters, so there is nothing for the description to clarify. The baseline of 4 is appropriate since no parameter documentation is needed.

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

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

The description clearly states the tool's action ('List') and resource ('all registered regulated entities'), making its purpose unmistakable. It distinguishes itself from the many sibling tools that perform actions or provide statuses, as this is a straightforward listing operation.

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 guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, intended use cases, or why one would choose entity_list over similar tools like onboard_entity or register_provider.

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 present, so the description carries full responsibility for behavioral disclosure. It implies a read-only operation through 'Get' but says nothing about return format, pagination, or potential side effects. The 'per entity' scope hint is minimal.

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, direct sentence with the verb front-loaded. No filler words or redundant explanations, making it easy to parse.

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 one optional parameter and no output schema, so the description should explain the response structure. It only lists data types, leaving the return format and relationship to escalation unclear.

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 entity_id already described as 'Entity ID (empty=all)'. The description's 'per entity' aligns with this but adds no new semantics beyond what the schema already states.

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 uses the specific verb 'Get' and names three distinct resources (findings, SLA breaches, escalation status) scoped per entity, making its function clear. It doesn't explicitly differentiate from sibling status tools, but the combination of resources is unique enough to avoid 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?

No guidance is provided on when to use this tool versus alternatives like run_escalation or article_status. The description only states what it retrieves, leaving the agent to infer appropriate usage contexts.

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 burden of disclosure. It does reveal what the evidence pack contains, but it does not mention side effects, output format, access requirements, or how the optional parameters affect 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 two short sentences, front-loaded with the action and resource. Every word earns its place; no filler or redundant restatement of the schema.

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 and no annotations, the description gives a helpful list of included content but leaves ambiguity around parameter combinations and return details. The all-optional parameter design makes this a notable 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 coverage is 100%, so the baseline is 3. The description adds that parameters refer to article/check/entity, but it does not clarify whether they are mutually exclusive, combinable, or what happens if none are provided.

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 uses a specific verb ('Export') and resource ('evidence pack'), further scoped to article/check/entity. The 'Pruefer-ready' phrase and listed contents (evidence, assessments, findings, audit trail, signatures) clearly distinguish it from sibling tools like evidence_summary.

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 intended use is implied by 'Export evidence pack' and 'Pruefer-ready', but there is no explicit guidance on when to prefer this tool over alternatives like evidence_summary or audit_trail. No exclusions or alternative references are 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?

With no annotations, the description carries the full burden of behavioral disclosure. It states the contents of the output but does not explain what happens when the optional entity_id is omitted, whether this is a read-only operation, or any pagination/sorting behavior. This leaves important behavior ambiguous 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?

The description is a single, front-loaded sentence with no filler words. It earns its place by naming the resource and key attributes, though it is terse enough to omit potentially useful context.

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 simple one-parameter tool with no output schema, so the description must convey both input meaning and output shape. It mentions evidence artefacts, hashes, and expiry dates, but does not explain the optionality of entity_id or the behavior when omitted, leaving the tool minimally viable but incomplete.

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 provides 100% coverage for the single entity_id parameter with the description 'Entity ID (optional)'. The tool description adds no deeper meaning about the parameter beyond tying it to 'an entity', so the baseline score 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 clearly states the tool returns all evidence artefacts for an entity, including hashes and expiry dates. It names the resource and content but lacks an explicit action verb like 'list' or 'get', and does not explicitly differentiate from sibling tools such as evidence_pack.

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 guidance is given on when to use this tool versus similar alternatives like evidence_pack or assess_all. The description only implies it is for retrieving evidence artefacts, with no exclusions, prerequisites, or preferred contexts.

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 the full burden. It discloses the main behavioral effect (expiring stale evidence and downgrading colors) and the condition (evidence too old), but it does not clarify whether changes are permanent, reversible, or what 'too old' means. The mutation effect is clear but lacks additional safety or side-effect 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 extremely concise—two short sentences—and immediately states the core purpose. No filler or redundant information; it earns every word.

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 is simple (one optional param), and the schema covers the parameter. However, there is no output schema and no annotation, so the description should at least convey what the tool returns (e.g., a list of affected IDs or new statuses). It also doesn't mention the overall scope when entity_id is omitted, though the schema hints at 'checks all'. Overall it's adequate for a simple watchdog but leaves some ambiguity about the result.

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

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

The schema coverage is 100% with a clear description for entity_id ('optional, checks all'). The tool description adds no parameter-specific detail beyond this, so the baseline of 3 is appropriate since the schema does the heavy lifting.

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 a specific verb ('Run') and resource ('freshness watchdog'), and details the exact action: expires stale evidence and downgrades statuses GREEN->YELLOW->GREY. This is sufficiently distinct from sibling tools like 'whatif_stale' or 'health_check'.

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 (run the watchdog to enforce freshness and downgrade old evidence) but provides no explicit when-to-use or alternative tool guidance. It doesn't mention prerequisites, frequency, or when not to use 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?

No annotations are provided, so the description carries the full burden of disclosing safety and side effects. It does not state whether this is a read-only report, what data sources it accesses, or whether it requires any setup. It does discuss the output characteristics (colors, priority, actions), but that is not sufficient behavioral transparency for a tool with no annotations.

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 concise sentence that front-loads the core purpose and includes key output details. Every word 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?

Given the tool has no annotations and no output schema, the description gives a reasonable high-level summary but omits important context such as how entity_id filters results, the meaning of the color codes, and the overall report format. It is adequate for a simple report tool but could be more complete for an agent to invoke it correctly.

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

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

The schema has 100% coverage for the single optional parameter entity_id, so the baseline is 3. The description does not elaborate on how entity_id affects the report, so no additional meaning is added beyond 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 identifies the tool's focus: DORA compliance gaps. It adds specific output characteristics (RED/GREY/YELLOW items, priority, required actions) that clarify the report's content, distinguishing it from more general assessment tools. However, it lacks an explicit verb like 'lists' or 'reports', relying on the tool name to imply the action.

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 guidance is given for when to use this tool over siblings like readiness_check or assess_all. The description implies it should be used for DORA gap reporting but provides no explicit context or exclusions. This is particularly important given the large number of similar compliance/assessment 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only lists report contents and does not explain side effects, permissions required, or whether generating a report mutates data. It also doesn't clarify the output behavior for different format values.

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 extremely concise, front-loaded with the primary action ('Generate...'), and uses a compact list to convey report contents. 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?

The description is incomplete in key respects: it mentions only a PDF report while the schema shows a 'format' parameter defaulting to 'json', and it doesn't explain the return values or meta vs. download behavior. With no output schema, this is a significant 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% with clear descriptions for both 'format' and 'entity_id'. The tool description adds no parameter-specific meaning beyond the schema baseline, so a score 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 clearly states the tool generates a 'DORA Ampel PDF report' with specific content areas (Score, gap analysis, provider register, audit trail integrity). This is a specific verb and resource, but it doesn't explicitly differentiate from sibling tools like gap_report or generate_trial_report, so it loses the sibling-distinction bonus.

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 guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites, exclusions, or scenarios where generate_report is preferable to sibling report 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?

The description mentions one behavioral trait (watermarked) but omits any side effects, permissions, or whether the operation is read-only. With no annotations provided, the description carries the full transparency burden and fails to disclose potential mutations or prerequisites.

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, concise sentence with no fluff. It front-loads the primary action and resource, but the undefined 'CTA' acronym slightly reduces clarity.

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 no annotations and no output schema, the description only covers the high-level purpose. It lacks parameter guidance and any indication of return format or behavior, leaving the agent under-informed for a simple but non-obvious 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 0% and the description says nothing about 'trial_id' or 'entity_id'. The agent has no information on what these parameters represent, making it impossible to invoke correctly with meaningful values.

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 action ('Generate') on a specific resource ('trial report') and lists key output components (score, gaps, CTA). It is clear and reasonably distinct from generic report tools like 'generate_report', though 'CTA' is unexplained.

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 guidance is provided on when to use this tool versus the many sibling report tools (e.g., generate_report, gap_report, bafin_report_draft). The single sentence gives no context for selection or 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?

With no annotations, the description carries the full burden of behavioral disclosure. It only says 'Server + DB status,' which implies a read-only check but does not explain response format, error behavior, permissions, or any side effects.

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 extremely concise with no wasted words. It is front-loaded but is a fragment rather than a full sentence, which slightly reduces clarity.

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

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

There is no output schema or annotations, so the description must convey return behavior. It only states 'status' without specifying what that entails (e.g., boolean, detailed JSON, error handling), leaving the agent uncertain about the tool's output.

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 has zero parameters, so the description has nothing to add. Baseline of 4 is appropriate since the schema is empty and there is no ambiguity to resolve.

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 'Server + DB status.' clearly identifies the resource (server and database) and implies the action (checking status). It distinguishes from siblings like article_status or bus_status by focusing on infrastructure, though it lacks an explicit verb.

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 guidance is provided on when to use this tool versus alternatives such as ping or bus_status. The description gives no context about appropriate usage scenarios or 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?

With no annotations provided, the description carries the full burden for behavioral disclosure. It states that each step creates signed evidence, which is a useful side-effect hint, but it does not disclose whether the tool mutates data, sends external notifications (implied by 'notify (BaFin)'), requires special permissions, or how steps interact. This is insufficient for a tool with no annotation safety profile.

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, tightly packed sentence with no filler. It front-loads the core concept (DORA incident lifecycle) and immediately lists the actions and a key side effect (signed evidence). Every phrase contributes meaningful 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?

Given the complexity (10 parameters, no required fields, no output schema, no annotations), the description is too minimal. It provides an overview but omits details about step-specific parameter requirements, the meaning of report_type or classification, the flow constraints, and the nature of the signed evidence output. An agent cannot reliably invoke this tool for all steps based solely on this description.

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 only 20% (only action and entity_id have descriptions). The description maps action values to lifecycle steps, which adds meaning to the central parameter, but it does not specify which of the other nine parameters are needed for each step, their formats, or their precedence. This leaves major ambiguity for a 10-parameter tool with no required fields.

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 identifies the tool as a DORA incident lifecycle with a clear set of actions (log, classify, notify, close). This conveys its purpose as managing incident steps, and the mention of BaFin notification and signed evidence distinguishes it from sibling tools like audit_trail or bafin_report_draft. However, it lacks an explicit verb like 'manage' or 'perform', making it slightly less direct.

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 guidance is provided on when to use this tool versus alternatives. The description does not mention preconditions, ordering constraints, or when to choose this over sibling tools like bafin_approve_send or audit_trail. The workflow list implies usage but does not state it explicitly.

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 transparency burden. It discloses the use of Claude API and the output format, but does not mention whether the operation is read-only, has side effects, or requires any permissions, leaving the agent with incomplete safety information.

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 short, front-loaded sentences: purpose, usage, and technology. There is no wasted wording or repetition, 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?

For a tool with two simple parameters and no output schema, the description covers the core function and output. It could note whether results are stored or purely computational, but the essential usage is sufficiently 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 input schema already provides descriptions for both parameters (contract_text, provider_name). The tool description adds minimal extra meaning beyond reiterating 'Paste contract text' and does not explain how provider_name affects the analysis, so it only meets the schema-coverage 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 explicitly states a specific verb and resource: 'LLM-based DORA Art. 30 contract analysis' and the output 'clause-by-clause PRESENT/PARTIAL/MISSING for all 15 mandatory clauses.' This clearly differentiates it from sibling tools like 'check_contract' or 'contract_analyze'.

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 instruction 'Paste contract text' provides clear context for use. However, it does not explicitly name alternatives or state when not to use this tool, so it stops short of a 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?

With no annotations, the description carries the full burden. It discloses that the tool performs multiple mutating actions: creates initial RED assessments, collects auto-evidence from live sources, and re-assesses. It also states the return value (readiness score). However, it does not address idempotency, reversibility, or prerequisites.

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?

Single sentence with a colon-led summary and comma-separated steps. It is front-loaded and contains no filler, making it easy to parse quickly.

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 one parameter, full schema coverage, no output schema, and no annotations, the description covers the main behavior and output. It lacks details on prerequisites or failure modes, but is adequate 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?

Input schema already documents the entity_id parameter with 100% coverage. The description does not add extra meaning about the parameter beyond referencing the entity, so baseline 3 applies.

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

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

The description opens with 'Full entity onboarding' and specifies the exact sequence: creates initial RED assessments for all 39 checks, collects auto-evidence, re-assesses, and returns readiness score. This clearly differentiates it from siblings like assess_all or readiness_check by describing a comprehensive onboarding workflow.

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 this is the tool for onboarding a new entity, but it does not explicitly state when to use it over alternatives like assess_all or create_entity. No exclusions or alternative tool mentions are 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?

With no annotations, the description carries the burden of behavioral disclosure. 'Quick connectivity test' implies a non-destructive, read-only action, but it does not explain what happens on failure, timing expectations, or any side effects. It provides minimal behavioral insight.

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 extremely concise: only four words. It is front-loaded and contains no filler. However, it is so brief that it sacrifices useful detail, though for a simple ping tool with no parameters, this level of brevity may be acceptable.

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 lacks context about what the tool returns, how to interpret results, or when to use it. Given there is no output schema, the description should explain the expected outcome or response. It also does not mention any prerequisites or limitations. The tool is simple, but the description is too sparse to be fully useful.

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 has zero parameters, so the schema already fully covers parameter documentation. Per the rubric, a baseline of 4 is appropriate. The description adds no parameter information, but none is needed.

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

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

The description states a specific purpose: 'Quick connectivity test.' It clearly indicates the tool tests connectivity and is quick, which is distinct from a generic action. However, it does not explicitly differentiate from sibling tools like health_check or freshness_check, which might also involve connectivity checks.

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 usage guidance is provided. The description does not mention when to use this tool vs alternatives, nor any exclusions. The only implication is that it is a 'quick' test, but there's no context about scenarios where this tool is preferred over others.

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 of behavioral disclosure. It mentions using entity data but does not disclose whether this is read-only, whether it persists/saves anything, or any permission/rate-limit requirements. For a generation tool, this lack of side-effect clarity is a notable 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?

Two concise sentences, front-loaded with the verb and resource. Every word adds value; lists the templates and data usage 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 tool's simplicity (2 params, no output schema, no annotations), the description covers purpose, templates, and data usage. It doesn't specify output format or side effects, but for a simple generation task, it is reasonably 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 only 50% (dora_article has a description, entity_id does not). The description compensates by explaining entity data is used for customization and by enumerating the 8 article templates, giving the agent the needed context for both parameters.

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 it generates DORA policy/framework document drafts, specifies the exact article templates (Art. 5,6,8,10,11,17,28,30), and notes customization via entity data. This specific action and resource distinguish it from sibling tools like bafin_report_draft or generate_report.

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 context for when to use: when generating a DORA article-specific policy draft using entity data. However, it does not explicitly state when not to use this tool or mention alternatives, so it stops short of a full guideline.

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 the full burden of disclosing behavior. 'Enrich' implies modification but does not state whether this is read-only, updates provider dependencies, or requires special permissions. It also leaves 'CLI' unexplained, and the absence of any note on side effects or output limits is a significant transparency 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 two concise sentences. The first conveys the core functionality with specific data points, and the second adds relevant regulatory context. No wasteful 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 single-parameter tool with no output schema and no annotations, the description provides the key data points and regulatory relevance. However, it does not clarify whether the tool returns enriched data or updates records, nor does it describe the output format. This leaves reasonable questions unanswered, so it is adequate but not 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 schema provides 100% coverage with a minimal description for entity_id ('Entity ID'). The description adds context that the tool operates on provider dependencies, but it does not explicitly map entity_id to a provider dependency or explain how the parameter affects the enrichment. This is adequate but not rich.

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: 'Enrich provider dependencies with OECD economic risk' and specifies the data elements (GDP, unemployment, CLI) per provider country. This distinguishes it from sibling tools like dependency_graph or whatif_provider by focusing on economic risk enrichment.

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 DORA Art. 28-31 reference provides clear context for when this tool is relevant (compliance with EU digital operational resilience). However, it does not explicitly exclude or compare against alternatives, so it falls short of a 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?

No annotations are provided, so the description fully carries the behavioral burden. It discloses output format and content, implying a read-only computation with no side effects. However, it doesn't mention prerequisites, permissions, or potential costs, which would be richer for a no-annotation tool.

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 entire description is one concise sentence that front-loads the core action and return values. Every word 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?

While the description explains return values well, it does not clarify the role of the optional entity_id or whether the score is organization-wide or scoped. Given the single optional parameter and straightforward output, this is mostly complete but lacks a small semantic piece.

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 optional parameter 'entity_id' is fully described in the input schema (100% coverage), so the description adds no additional parameter semantics. The baseline of 3 applies as the schema does the heavy lifting.

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 computes a 'Full DORA readiness score' with an 'Ampel per article', specifying exact output ranges (GREEN/YELLOW/RED/GREY, 0-100) and scope (all 26 articles). This distinctively separates it from generic siblings like health_check or assess_all.

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 implicit usage context for DORA readiness assessments but does not explicitly mention alternatives or exclusions. It clearly implies when to use this tool, but lacks explicit 'when not to use' guidance compared to 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?

Without annotations, this description carries the full burden. It discloses that the tool stores provider data and creates evidence, but does not specify side effects, permissions, idempotency, or what 'creates evidence' entails.

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 extremely concise, consisting of two short sentences. It front-loads the primary action and avoids 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 13 parameters, no annotations, and no output schema, this two-sentence description is insufficient. It doesn't explain the evidence creation, any prerequisites, or important parameter semantics, making it incomplete for a tool of this complexity.

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 does not mention any of the 13 parameters, and the schema has only 54% parameter coverage. It adds no extra meaning to the input schema, leaving undocumented parameters without explanation.

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 explicitly states the tool registers an ICT third-party provider for the DORA Art. 28 Register of Information, and mentions storing provider data and creating evidence. It clearly identifies the specific resource and action, making it distinct from similar tools like 'onboard_entity'.

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 for usage (DORA Art. 28 register), but does not explicitly address when to use this tool over alternatives or mention exclusions. No sibling comparison is given.

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 the full burden. The verb 'Show' implies a read-only operation, and the mapping is disclosed, but there is no mention of output format, error handling, or prerequisites. This is adequate for a simple tool but not richly 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?

The description is two short sentences, front-loaded with the primary action and resource, and every word contributes value. 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?

For a tool with a single parameter and no output schema, the description adequately conveys what it does and the mapping logic. It lacks explicit return structure, but the phrasing 'Maps DORA → MiCA + AMLR' hints at the output. Given the tool's simplicity, this is nearly 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% for the single parameter, providing the parameter name and example. The description's phrase 'specific DORA article' aligns with but does not add meaning beyond the schema. 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 clearly states the verb 'Show' and a specific resource: cross-regulation impacts for a given DORA article. It further clarifies the scope by mapping DORA to MiCA and AMLR, which distinguishes it from generic siblings like cross_regulation_check.

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 a specific DORA article but does not explicitly state when to choose this over alternatives or provide exclusion criteria. No sibling tools are referenced, so guidance is only implicit.

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 responsibility for behavioral disclosure. It reveals that the tool scrapes external websites and returns alerts, which is useful. However, it does not mention potential side effects such as network rate limits, authentication requirements, or error handling, leaving some uncertainty about operational constraints.

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, consisting of two sentences that front-load the core function and then provide usage guidance. Every sentence adds value: the first explains what the tool does and returns, the second explains when to run it. No unnecessary filler or repetition of the tool name.

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 only one optional parameter and no output schema, the description provides sufficient context: it names the data sources, the regulation monitored, the return value (alerts with articles and severity), and suggested usage. It could be slightly more complete by detailing the structure of the returned alerts, but the essentials are 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?

The input schema covers the single parameter 'days_back' with a clear description ('Check items from last N days (default: 7)'), giving 100% schema_description_coverage. The tool description does not add any additional parameter semantics beyond what the schema already provides, so the baseline score 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 clearly states the tool's function with a specific verb ('scrapes') and explicit resources (EBA/ESMA/BaFin/CERT-Bund) for DORA updates. It also specifies the output (alerts with affected articles and severity), which distinguishes it from sibling tools that focus on assessments, reporting, or contract analysis.

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 scheduling guidance ('Run daily via cron or on-demand'), which implies the tool is intended for periodic monitoring. It does not explicitly name alternatives or exclusions, but among the listed siblings, no other tool appears to perform regulatory scraping, making the intended use 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 are provided, so the description carries the burden. It discloses key side-effect behavior (auto-close if GREEN) and the multi-step process, but does not elaborate on permissions, reversibility, or what happens if not GREEN. This is moderate transparency.

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 two concise sentences, front-loaded with the action and outcome. Every word adds value, and it does not repeat schema details unnecessarily.

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 simple tool with one parameter and no output schema, the description provides sufficient context: it explains the purpose, the process, and the automatic closure behavior. It lacks detail on the return format, but that is not critical given the 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?

The input schema has 100% coverage for the single parameter finding_id, which already describes it as 'Finding ID to re-test'. The description adds no extra parameter semantics beyond what the schema provides, so baseline 3 applies.

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

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

The description uses a specific verb 'Re-test' with a clear resource 'a finding' and outlines the process: collect fresh evidence, reassess check, auto-close if GREEN. This clearly distinguishes it from sibling tools like update_finding or assess_all.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool: when a finding needs re-testing with a closed-loop outcome. It does not explicitly mention alternatives or exclusions, but the context is clear enough for an agent to select it appropriately.

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 full behavioral disclosure burden. It mentions key side effects ('auto-create findings', 'escalate'), but omits details about reversibility, permissions, external impacts, or what happens after escalation. The caller is not warned about potential irreversible actions or required authorities.

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 concise, front-loaded sentence with no filler. Every element adds value: trigger action, engine, and the three concrete sub-behaviors.

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 trigger with no output schema, the description lists the main postconditions (findings creation, SLA check, escalation). It does not describe the return value or detailed flow, but the core behavior is adequately captured 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?

The tool has zero parameters, so there is nothing for the description to explain about individual inputs. Baseline for no parameters is 4; schema coverage is trivially 100%.

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 names a specific verb ('Trigger') and resource ('escalation engine'), and enumerates concrete actions ('auto-create findings, check SLA, escalate'). This clearly distinguishes it from siblings like escalation_status, which would only check status.

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: it is used to trigger the escalation engine. However, there is no explicit guidance on when to choose this over alternatives such as escalation_status or assess_all, nor any 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses that the tool returns 'score, gaps, automation potential', which gives some output expectations, but it does not state whether the tool is read-only, modifies data, requires permissions, or behaves differently under certain 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 two short sentences with no redundant information. It front-loads the core action and then states return values. 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?

Given no annotations, no output schema, and zero parameter coverage, the description is incomplete. It provides the purpose and basic return value but misses parameter details, usage context, edge cases, and safety or side-effect information that would be necessary for an agent to confidently invoke the 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 0%, and the description does not explain the parameters (trial_id, entity_id) beyond implying they relate to a trial entity. Neither the schema nor the description provides semantics for these parameters, so the agent has no idea what values to supply.

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 action ('Run complete DORA+MiCA assessment') and the resource ('trial entity'), which is a specific verb+resource pair. It distinguishes from siblings like assess_all by scoping to a trial entity and the DORA+MiCA framework, though it doesn't explicitly name alternatives.

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 guidance is given on when to use this tool versus others. It doesn't mention alternative tools like assess_all or cross_regulation_check, nor does it state exclusions or prerequisites. The only contextual hint is 'trial entity', but this is not enough to guide tool selection.

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 burden of behavioral disclosure. It adds useful details about the analysis dimensions (weekly deltas, trajectory, peer benchmark) and states it shows improvement/decline. However, it does not mention any prerequisites, limitations, or what happens if historical data is missing, leaving moderate transparency.

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 sentence with a clear verb, front-loaded purpose, and specific details. Every word contributes to understanding the tool's behavior 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?

For a simple tool with one parameter and no output schema, the description adequately covers the main behavior and key outputs. It lacks explicit details on return format or data prerequisites, but these are not critical for a straightforward analytical tool. A higher score would require more explicit output description.

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 has 100% coverage for the single parameter (entity_id) with a clear description. The tool description adds no extra parameter semantics beyond what the schema provides, which is acceptable given the high 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's function: showing score trend over time, with specific features (weekly deltas, trajectory, peer benchmark) and outcome (improvement/decline). This distinguishes it from sibling tools like article_status or assess_all, which focus on current state rather than temporal trends.

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 analyzing score evolution over time, providing clear context. However, it does not explicitly mention when not to use it or name alternative tools, so it falls short of the top score which requires explicit when/when-not/alternatives.

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 the full burden of disclosing behavioral traits. It states return values (stats, classification, resolution rates) but does not clarify whether the sync operation has side effects, requires specific permissions, or is read-only. The word 'sync' implies potential mutation without elaboration.

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 very concise, using a few short fragments to convey purpose, context, and output. It avoids filler, though the fragment style and abbreviation (DORA Art. 17/21) slightly reduce readability.

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 no output schema, the description provides useful output information and regulatory context, but it leaves ambiguity around the sync operation's behavior and response format. This is a moderate level of completeness—adequate but with clear 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?

The schema description covers 100% of the single parameter (days_back) with a clear description and default value. The tool description adds no extra parameter meaning, so a 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 identifies the tool as ServiceNow incident + change management sync, and clarifies it provides DORA Art. 17/21 evidence with output of 30-day incident stats, classification, and resolution rates. The verb 'sync' is somewhat ambiguous—whether it performs a retrieval or an active synchronization—but the output description narrows the purpose sufficiently.

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 explicit guidance on when to use this tool vs. alternatives like incident_flow or evidence_pack. The mention of DORA Art. 17/21 gives domain context but no concrete selection criteria or 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose the state transition diagram, which is a meaningful behavioral trait. However, it omits details about permissions, idempotency, failure modes, or whether the actions are mutually exclusive, leaving partial transparency.

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 exactly two sentences that front-load the purpose and enumerate the actions, followed by the status flow. There is no waste or redundancy; every sentence 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?

Given the tool's complexity (8 parameters, a state machine, no output schema, and no annotations), the description provides a useful overview of the lifecycle but lacks per-action parameter requirements, return values, or validation rules. It is coherent but not 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 input schema provides 100% description coverage for all parameters, so the baseline is 3. The description adds lifecycle context but does not provide additional meaning to individual parameters beyond what the schema already states (e.g., 'owner' for claim). No extra semantic value is contributed.

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 uses the specific verb 'Update' with the resource 'finding lifecycle' and enumerates the concrete actions ('claim, set remediation plan, request re-test, close, or accept risk'). This clearly conveys the tool's purpose and differentiates it from siblings like article_status, though it does not explicitly contrast with retest_finding.

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 action list and the status flow ('open -> in_progress -> retest_pending -> closed | risk_accepted') imply when to use the tool and what transitions are allowed. However, there is no explicit guidance on when not to use this tool or when to prefer a sibling like retest_finding, so the usage context is implied rather than fully spelled out.

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 the full burden of behavioral disclosure. It says 'Simulate', which implies a non-destructive read-only operation, and it lists the outputs (affected items, impact score, risk level). However, it does not explicitly confirm that no state changes occur, nor does it mention whether any side effects (e.g., report generation) or prerequisites (e.g., provider must be configured) 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?

The description is a single concise sentence that front-loads the primary action ('Simulate provider failure') and then lists the outputs. Every word contributes useful information; there is no verbose repetition or vague 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?

The description provides the essential purpose and outputs (affected items, impact score, risk level), which is a reasonable starting point. However, with no output schema and no annotations, it lacks details on how to interpret the returned values, how to handle optional params, and what the tool does if no entity_id or provider_name is given. For a tool with only two optional params and a specific simulation scenario, this is adequate but not 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 input schema has 100% coverage with descriptions for both parameters ('Entity ID' and 'Provider name (e.g. AWS, Finastra)'), so the baseline is 3. The description adds some context by framing provider_name as the provider to fail and entity_id as the scope, but it does not clarify whether one parameter is required, how they interact, or what happens if omitted. Since the schema descriptions are minimal and tautological for entity_id, the tool description adds limited additional meaning.

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 a specific action ('Simulate provider failure') and resource ('provider'), and enumerates the outputs ('which articles/checks are affected, score impact, risk level'). This is a specific verb+resource+output structure that distinguishes it from sibling tools like whatif_stale (which targets stale what-if scenarios) and assess_all (general assessment).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (when you want to evaluate the impact of a provider failure on articles/checks), but it does not explicitly state when to prefer this over alternatives like whatif_stale or provider_country_risk. No exclusions or alternative guidance is provided, leaving some ambiguity in tool selection.

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 behavioral burden. It suggests a non-destructive 'simulate' operation but does not disclose whether it mutates state, requires permissions, returns a report, or has side effects. This is insufficient for a tool with zero annotation coverage.

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 action and the scenario without any filler. Every word contributes meaning, making it highly concise and efficiently 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?

The tool has three optional parameters and no output schema, yet the description does not explain what the simulation returns, how the identifiers are used, or what 'stale' means. It leaves significant gaps that are not compensated by annotations or output schema, so the overall context is incomplete.

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 field descriptions already providing baseline semantics. The description adds context by mapping 'N days' to the days parameter and tying the scenario to 'stale evidence', but it does not explain the relationship between check_id and entity_id or their optionality in detail.

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 uses the specific verb 'Simulate' with the resource 'stale evidence' and states the scenario 'if a check stays stale for N days'. This clearly defines the tool's purpose and distinguishes it from siblings like whatif_provider, which focuses on provider scenarios.

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 guidance is given on when to use this tool versus alternatives such as freshness_check or whatif_provider. The simulation intent is implied, but there are no explicit context cues, exclusions, or recommendations, leaving the agent to infer suitability.

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