incidentoracle

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

With no annotations, the description must disclose behavioral traits, but it only states the classification result. It does not mention whether the tool reads existing incident data, whether it requires all inputs, what it returns beyond the label, or whether it has side effects. The reference to '4h/72h/1m reporting' hints at consequences of classification but not at tool 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 sentences with no fluff. It leads with the action verb 'Classify', specifies the regulatory framework, and defines the output categories. 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 the tool has 7 parameters, no output schema, and no annotations, the description is too sparse. It explains the high-level purpose but does not cover input expectations, return values, or how thresholds are applied. For a relatively complex tool, this is insufficient for reliable 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 description coverage is 57%, so the description must compensate for undocumented parameters (incident_id, duration_hours, economic_impact_eur). It does not. The description references DORA criteria but fails to map any input fields to specific criteria or explain how the tool uses them. This leaves the agent guessing about critical inputs.

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 'classify an incident against the 6 DORA criteria' and identifies the binary outcome (MAJOR vs NON-MAJOR). It names a specific regulation, making the purpose concrete. However, it does not differentiate from the sibling tool 'major_incident_check', which likely serves a similar purpose, so it misses the full 5.

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 its alternatives. The description implies classification for DORA compliance but does not state prerequisites, exclusions, or when a different tool like 'major_incident_check' might be more appropriate.

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 mentions the Annex III template and voluntary nature, but fails to disclose side effects, required permissions, or what happens after submission. It doesn't specify whether the notification is stored, forwarded, or validated, making it insufficient for an agent to anticipate consequences.

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 present purpose and template context with minimal waste. Each sentence contributes necessary information, making it highly concise and 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?

For a tool with 8 parameters, no annotations, no output schema, and no parameter descriptions, the description is too sparse to enable correct invocation. It lacks guidance on required fields, parameter formats, or relationship to sibling notification tools, leaving significant 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?

The schema has 8 string parameters with 0% description coverage, and the description provides no parameter-level meaning. It only references the template, which vaguely implies structure but does not explain fields like iocs, ttps, or affected_systems. The low coverage requires compensation that the description does not provide.

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 as a voluntary notification for significant cyber threats, referencing specific legal context (Art. 19(2)) and a template (ITS 2025/302 Annex III). It distinguishes from sibling tools like initial_notification by emphasizing 'voluntary' and 'threat' rather than incident 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 description implies usage for voluntary threat notifications under Art. 19(2), suggesting it's for non-mandatory reporting. However, it does not explicitly state when not to use it or mention alternative tools like initial_notification or intermediate_report, leaving the when-to-use guidance implicit rather than explicit.

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

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

With no annotations provided, the description carries the behavioral disclosure burden. It discloses the scope ('active MAJOR incident reporting deadlines') and the output content ('overdue and upcoming'), which gives some behavioral context. However, it does not mention read-only nature, permissions, or any side effects, leaving gaps for a tool with no 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?

Two concise sentences with no redundant information. The description is front-loaded with the main purpose and immediately clarifies the output, 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?

For a zero-parameter, relatively simple dashboard tool, the description covers the core functionality (tracking deadlines, showing overdue/upcoming). While it could add details like timezone or grouping, the simplicity and lack of parameters make the description adequately complete.

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

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

The tool has zero parameters and an empty schema, so there is nothing to explain. The description appropriately focuses on the tool's purpose. Consistent with the baseline for 0-parameter tools.

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 ('Track') and resource ('MAJOR incident reporting deadlines'), and further specifies the output ('Shows overdue and upcoming'). This distinguishes it from sibling tools like initial_notification or final_report, which are for creating reports, not tracking deadlines.

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 checking the status of incident reporting deadlines, but it does not explicitly state when to use this tool versus alternatives or mention any exclusions. It gives no direct comparison to sibling tools, so the 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. The verb 'Generate' is ambiguous: it doesn't state if the tool is read-only, if it creates or updates a record, or if specific permissions are required. There is no mention of side effects or data persistence, leaving the agent uncertain about the operation's impact.

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. It efficiently states the main action and the report's key contents, but given the parameter complexity, it could be more structured (e.g., bullet points or usage notes) without adding excessive length.

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 8 parameters, no annotations, and no output schema, the description is notably incomplete. It lacks guidance on when to use the tool (beyond implied timing), how the many parameters relate, what inputs are essential, and what the agent should expect as a result. An agent would struggle to choose and invoke this 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 has 8 parameters with zero description coverage, so the description must compensate. It only hints at two fields ('root cause analysis' and 'lessons learned') but does not explain that incident_id is required or what total_cost_eur, resolved_at, recovery_actions, etc. are for. This is far from sufficient for correct invocation.

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

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

The description uses a specific verb ('Generate') and a clear resource ('the 1-month final report'), with scope ('root cause analysis and lessons learned'). This distinguishes it from sibling tools like intermediate_report and initial_notification by specifying the final month-end deliverable.

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 '1-month final report' implies it should be used at the end of an incident month, but no explicit when-to-use or alternative guidance is provided. It doesn't say 'use this instead of intermediate_report' or list any exclusions, so the usage context 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?

With no annotations, the description carries the full burden of behavioral disclosure, but it only says 'Server status.' It fails to mention side effects, return format, or operational behavior. The read-only nature is implied but not explicitly stated.

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 two-word description is extremely concise and front-loaded, containing no redundancy. However, it is under-specified, which keeps it from a perfect score even though brevity itself is handled well.

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's simplicity, there is no output schema or annotations, so the agent receives no information about return values, error cases, or side effects. 'Server status.' is too incomplete for confident invocation without additional inference.

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 zero parameters, so there is no parameter semantics burden. The description does not need to elaborate on inputs, and the baseline of 4 for a 0-parameter tool 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 names the resource ('server') and concept ('status') but lacks an explicit verb, making it vague about whether this checks, retrieves, or reports status. It is distinguishable from the incident-focused sibling tools, but it does not clearly state the tool's action or scope.

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

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

No usage context is provided. The description gives no guidance on when to use health_check versus sibling tools like major_incident_check, nor any exclusions, prerequisites, or 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 behavioral disclosure. It mentions 'full register' and filters but does not state whether the tool is read-only, how results are returned (pagination, structure), whether it requires authorization, or what 'full' means. The behavior beyond filtering is left 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 a single, front-loaded sentence that immediately communicates the tool's purpose and key options. Every word earns its place, with no redundant or filler content.

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 4 parameters, no output schema, and no annotations. The description provides only a high-level overview of filters but omits crucial context such as the return value structure, pagination behavior, whether filters are combinable, and any response format. An agent could select the tool but would lack sufficient information to handle its output confidently.

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 names all four parameters as filters, which aligns with the schema properties. However, it adds no detail beyond the property names: 'search' is ambiguous (matches what? incident ID, summary?), and the enums are left entirely to the schema. Given zero schema description coverage, the description only minimally compensates.

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 the resource ('full incident register') and its filtering capabilities, clearly distinguishing it from create/update siblings like log_incident and from statistical tools like incident_stats. However, it lacks an explicit verb like 'list' or 'get', making the operation 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?

The description implies the tool is for browsing/filtering the incident register via the listed filters, but provides no explicit guidance on when to choose it over alternatives such as incident_stats or final_report. There are no exclusions or alternative recommendations.

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 describes the scope of metrics but does not explicitly state that this is a read-only operation, nor does it mention permissions, rate limits, or side effects. The word 'Dashboard' implies read-only, but it is not 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 concise line that front-loads the key information. Every word contributes to conveying the tool's purpose, with no filler or repetition.

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 no parameters and no output schema. The description enumerates the main metrics included in the dashboard, providing a reasonable overview. However, it does not describe the response structure or explicitly confirm it is a read-only endpoint, leaving some 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, and the empty input schema fully describes the interface. There is nothing to compensate for, so the baseline of 4 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 indicates a dashboard of incident statistics, listing specific metrics (total/open/major incidents, overdue deadlines) and grouping by severity/status. It distinguishes from sibling tools that perform actions like classify, notify, or log, though it lacks an explicit verb such as 'retrieves' or 'displays'.

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 related tools, leaving usage entirely implied by the term 'Dashboard'.

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 adds useful context about the regulatory deadline and severity classification, but does not describe the output format, whether the notification is submitted automatically, or any side effects. The verb 'Generate' implies creation of content, but more detail would improve 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 sentences long, immediately front-loads the action, and includes the critical deadline. Every sentence earns its place with no wasted words. It is concise and well-structured for an agent 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?

Given the tool has 6 parameters, no annotations, and no output schema, the description is relatively sparse. It provides essential regulatory context and timing, but lacks information about parameter usage, expected output, and how it fits with sibling incident workflow tools. It is minimally adequate for an agent to understand the tool's purpose but not fully complete for invocation decisions.

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 33% (only authority and affected_states have descriptions). The description itself mentions no parameters and does not compensate for the low coverage. The required incident_id is not explained beyond the schema, and discovery_method's enum values are not clarified. The description adds no value in helping the agent understand how to fill 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 states the action with a specific verb and resource: 'Generate the 4h initial notification.' It further specifies 'for a MAJOR incident' and references 'ITS 2025/302 Annex I', making it distinct from sibling reporting tools like intermediate_report or final_report. The purpose is unambiguous and well-scoped.

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

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

The description provides explicit timing constraints ('Must be submitted within 4h of classification, max 24h after detection') and scopes the tool to MAJOR incidents. It does not explicitly name alternatives or exclusions, but the regulatory deadline and severity scope give clear context for when to use this tool versus other reporting steps.

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 provides minimal behavioral context beyond the action-plan requirement. It does not disclose side effects, required prior conditions, output behavior, or who receives the report.

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 tool's core purpose and a critical conditional requirement. 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?

Despite having 7 parameters and no annotations or output schema, the description only covers the report's purpose and one condition. It omits parameter semantics, behavior, and return/output details, leaving significant 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?

Schema coverage is 0% and the description does not explain any of the 7 parameters. The only indirect hint is the action_plan requirement, but the meaning of recovery_status, containment_actions, expected_resolution, etc., is left entirely to the schema.

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

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

Clearly identifies the tool as generating the 72h intermediate report for major incidents (ITS 2025/302), using a specific verb and resource. This distinguishes it from sibling tools like initial_notification and final_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 description implies the use case: 72 hours into a major incident, and notes when resolution is pending. However, it does not explicitly mention when not to use it or point to alternative tools like final_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?

No annotations are provided, so the description carries the full burden. It states that the tool logs an incident but does not disclose important behavioral aspects such as whether it creates a persistent record, triggers notifications, requires specific permissions, or is reversible. For a mutation tool with 17 parameters, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences with no wasted words. It front-loads the core purpose and adds a single, useful process context sentence.

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

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

Given the tool has 17 parameters, no output schema, and no annotations, the description is far too thin. It does not address what data is needed for a complete incident log, what the tool returns, or any prerequisites or side effects, making it inadequate for correct and complete 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 description coverage is only 12%, and the description adds no meaning for any of the 17 parameters. With many parameters like 'data_losses', 'geographic_spread', and 'economic_impact_eur' left undocumented, the description fails to compensate for the low coverage.

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

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

The description clearly states the verb 'Log' and specific resource 'new ICT-related incident', and adds process context 'First step in the DORA incident management process'. This distinguishes it from siblings like 'incident_log' (likely a read operation) and 'classify_incident' (a later step), 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?

It provides clear usage context: use as the first step in the DORA incident management process. This implies it should precede classification and other post-incident steps, but it does not explicitly state when not to use it or name alternative tools for related actions.

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, the description carries the burden of disclosing behavior. It states 'No incident record needed,' suggesting a non-persistent check, but doesn't mention side effects, output format, or any other behavioral details.

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 worded sentence that front-loads the purpose and includes a useful qualifier about not needing an incident record. 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?

With six undocumented parameters, no output schema, and no annotations, the description is too sparse to fully inform an agent. It clarifies the high-level purpose but doesn't explain how to populate inputs or interpret the classification 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 has zero parameter descriptions (0% coverage), and the description makes no attempt to explain the six parameters or their values. Phrases like 'criteria values' are generic and don't add meaning beyond the bare parameter names in the schema.

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

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

The description clearly states the tool checks if criteria values classify as a MAJOR incident, using a specific verb ('check') and resource ('criteria values'), and distinguishes from record-creating tools by saying 'No incident record needed.'

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 the tool ('for pre-assessment') and implies when not to use it ('No incident record needed'), but it doesn't name specific alternative tools or provide 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?

With no annotations, the description carries the full burden for behavioral disclosure. It does reveal that 'competent authority must be notified of reclassification,' which is a meaningful side-effect. However, other potential behaviors—such as updating the incident record, reversibility, or consequences—are not disclosed, leaving notable 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 a model of conciseness: two short sentences, no redundancy, and front-loaded with the primary action. The second sentence adds a crucial requirement, ensuring every word earns its place.

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

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

For a simple tool with three parameters and no output schema, the description covers the core action and a key notification requirement. It could be improved by explicitly mentioning that the incident is updated and perhaps that the reason field is for documentation, but overall it is sufficiently complete for the tool's simplicity.

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

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

Schema description coverage is 0%, so the description must compensate for missing parameter documentation. It does mention the classification values MAJOR/NON-MAJOR, but these are already visible in the schema's enum. It offers no explanation of incident_id or the optional reason parameter, adding minimal value beyond the structured schema.

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

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

The description clearly states the tool's purpose: reclassifying an incident between MAJOR and NON-MAJOR. It uses a specific verb (reclassify) and resource (incident), and the phrase 'or vice versa' clarifies bidirectional capability. However, it does not explicitly differentiate itself from the sibling tool classify_incident, which may handle initial classification.

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 that it applies to existing incidents or how it differs from classifies_incident. There are no prerequisites, exclusions, or alternative tool references, leaving the agent to infer usage context.

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