nucleus

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

Annotations declare readOnlyHint=false, openWorldHint=true, destructiveHint=false. The description adds HITL requirement for spawn_agent and lists mutation actions, but does not detail side effects, permissions, or rate limits. Some behavioral context is provided, but not comprehensive.

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?

Organized as a bulleted list with a summary header. Each action is described in one line, making it scannable. No redundant sentences, though the list format is lengthy.

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 (16 sub-actions, output schema exists), the description provides a high-level overview but lacks details on return values, error handling, and when to use specific sub-actions. 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 is generic (action string + params object) with 0% parameter description coverage. The description compensates by listing each action's parameters with brief notes (e.g., 'require confirm=true'). This adds meaningful context beyond the schema.

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

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

The description states the tool covers 'Agent spawning, critic, swarm, memory, ingestion & dashboard tools.' This provides a broad category but lacks a single specific verb-resource statement. It lists many sub-actions, making the overall purpose somewhat clear but not sharply distinguished from sibling tools.

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

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

No explicit guidance on when to use this tool versus sibling tools like nucleus_audit or nucleus_governance. The description does not provide context or alternatives, leaving the agent to infer usage from the action names 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?

The description contradicts the readOnlyHint annotation with the log_event action being a write operation. It does not acknowledge this or clarify side effects aside from admin_query logging.

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

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

The description is well-structured with bullet points and code formatting. It is relatively concise given the multiple actions, though some redundancy exists.

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

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

The description covers the main actions and their parameters but omits return values and error handling. The output schema exists but its content is unknown, so completeness is moderate.

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 only two high-level fields with minimal constraints, but the description lists action-specific parameters, compensating for the 0% schema coverage. However, it lacks detail on parameter types and formats.

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

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

The description clearly states it is an audit log with a hash chain, listing the available actions. It distinguishes the tool from siblings by specifying its team-tier and tamper-evident nature.

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 some usage context by explaining admin_token requirement for admin_query and rejection of team_id='*' in query. However, it does not explicitly explain when to choose this tool over siblings.

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

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

Annotations are basic (readOnlyHint=false, etc.), but the description adds valuable behavioral context: it's a one-shot convenience that creates a long-poll subscription, server detects role from environment variables, and timeout_seconds has a default and range. No contradictions with annotations. Slight deduction for not discussing potential side effects like duplicate subscriptions.

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

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

The description is front-loaded with the main purpose. It includes some internal references (PR #2, IDE-agnostic) that may not be universally helpful, but overall every sentence adds value. Slightly verbose but justified by complexity.

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

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

Given the tool's complexity (combining two operations), the presence of an output schema, full schema parameter coverage, and sibling context, the description is remarkably complete. It covers purpose, usage, parameter semantics, and differentiation from alternatives, leaving no major 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?

Schema coverage is 100%, providing baseline 3. The description adds context beyond the schema: role can be explicitly overridden but server auto-detects if omitted, and timeout_seconds has a default tied to FastMCP context-cache TTL. This adds meaningful usage guidance.

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: 'resolve canonical inbox + arm long-poll subscription'. It distinguishes itself from the sibling tool nucleus_relay_subscribe by explaining that it hides the step of knowing the canonical inbox name, making it a convenience entry point.

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

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

The description explicitly states why this tool exists vs nucleus_relay_subscribe + inbox_filter, and recommends it as the 'RECOMMENDED entry point for SessionStart auto-arming'. It provides clear context for when to use this tool over its 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?

Annotations already indicate readOnlyHint=false and destructiveHint=false. The description details each action's behavior (e.g., 'write_engram' is a write operation, 'health' is read-only) but does not go beyond what the actions imply. No contradiction with 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 excessively long (over 30 lines) listing many sub-actions. While it is structured as a bullet list, it lacks conciseness. Key details are buried, and a more compact summary with links to separate definitions would be better.

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 (32 sub-actions) and the existence of an output schema (not shown), the description covers each action's purpose and most parameters. Missing operational context like error handling or rate limits prevents a perfect score.

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 is minimal (action + params object), but the description compensates fully by listing and explaining parameters for each action (e.g., write_engram: key, value, context?, intensity?). Schema description coverage is 0%, so the description provides essential information that the schema lacks.

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 covers 'Engrams, health, observability, DSoR & tier system tools' and lists many specific actions, each with a concise one-line purpose. It distinguishes itself from siblings (e.g., nucleus_agents) by focusing on engram/memory operations and system 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 description implies usage by listing actions but does not explicitly state when to use this tool over alternatives or provide exclusion criteria. For a meta-tool with many sub-actions, more explicit guidance would help an agent decide.

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

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

Annotations indicate readOnlyHint=false and destructiveHint=false, but the description does not elaborate on behavioral traits like mutability or side effects. It merely lists actions, which implies mutability for some but lacks explicit disclosure.

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

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

The description is front-loaded with a summary and organized as a list of actions. It is somewhat verbose but structured for readability. Minor redundancy exists (e.g., 'Actions:' header is helpful).

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

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

The description covers all sub-actions and their parameters, but lacks return value explanations (though output schema exists). It does not address error handling, prerequisites, or per-action usage context, which is notable given the tool's 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 input schema is generic (action + params), providing no parameter details. The description compensates fully by enumerating each action and its specific parameters, which is critical 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 clearly states 'Feature tracking, proof generation & MCP server mounting' as the purpose, and distinguishes it from sibling tools like nucleus_agents or nucleus_governance. However, the tool is multi-action, which slightly dilutes focus.

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

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

No guidance is provided on when to use this tool versus alternatives. The description lists sub-actions but does not explain the context or prerequisites for choosing this tool over siblings.

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

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

Annotations already declare readOnlyHint=false and destructiveHint=false, indicating potential mutation without destruction. The description lists actions like join, leave, and sync, which are consistent with these traits. However, it does not disclose additional behavioral details (e.g., whether route requires authorization, or what happens during sync). With annotations present, the description adds minimal extra 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 concise, starting with a clear purpose statement followed by a bulleted list of actions. Each action has a one-line description. There is no extraneous information, though the list could benefit from slightly more 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?

Given the tool's complexity (multiple sub-actions) and a vague input schema, the description lacks completeness. It does not explain return values, error scenarios, or dependencies (e.g., must be in a federation to leave). With an output schema available but not described, the agent is left without guidance on expected responses.

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 is generic (action + params object), with 0% description coverage. The description partially compensates by listing expected parameters for join (seed_peer) and route (task_id, profile?). However, it does not fully define parameter structures or types, leaving significant ambiguity for the agent.

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 title 'Federation' and description 'Federation management for multi-brain coordination' clearly indicate the tool's domain. The action list (status, join, leave, peers, sync, route, health) provides specific verbs and resources. However, it does not explicitly differentiate from sibling tools like nucleus_route or nucleus_sync, which could have overlapping functionality.

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 merely lists actions without explaining context, prerequisites, or when not to use it. For a multi-action tool, this is a significant gap.

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

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

Annotations provide destructiveHint true, and the description adds behavioral details: e.g., delete_file requires confirm=true (HITL), lock/unlock change file immutability, curl/pip_install are proxied. This adds significant context beyond 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 well-structured as a bullet list with concise lines per action. It starts with a summary line. Though lengthy due to many actions, each line is informative and free of fluff.

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

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

Given the tool's complexity (15+ sub-actions) and minimal schema, the description covers each action's purpose and parameters. With an output schema present, return values need not be detailed. Adequately complete for a dispatcher tool.

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

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

The input schema is generic with only action and params, but the description lists each sub-action with its specific parameters, fully compensating for the lack of schema coverage. Each action's parameters are explicitly named, providing essential 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 'Governance, Hypervisor & security tools for the Nucleus Agent OS' and lists sub-actions with brief explanations. While purpose is clear, it's broad as a dispatcher; the tool aggregates many operations, making it distinct from sibling tools.

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

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

Tags like [HYPERVISOR] and [GOVERNANCE] provide context, but no explicit guidance on when to use this tool vs. alternatives (e.g., nucleus_tasks). The sub-action descriptions imply usage for specific tasks but lack when-not suggestions.

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

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

Annotations indicate destructiveHint=true and readOnlyHint=false, but the description adds no further behavioral context (e.g., auth needs, side effects, state changes). For example, 'manage_strategy' and 'update_roadmap' imply writes, but no specifics on what gets modified.

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

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

The description is well-structured with a clear intro and bullet-like list of actions. It is concise given the number of sub-actions, with each line providing a short description. A minor improvement would be grouping related actions.

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 an output schema (from context), the description does not explain return values or how results are structured. For a complex dispatcher tool with multiple sub-actions, more detail on behavior and outcomes is needed.

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

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

The input schema is generic with only 'action' and 'params'. The description adds value by listing valid actions and mentioning parameters for some (e.g., 'params: {project?, region?}' for gcloud_services). However, coverage is incomplete—many actions lack parameter hints, and the schema does not define action enum 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 clearly states the tool's domain: 'Infrastructure: file changes, cloud, marketing & strategy tools.' It lists sub-actions, giving a specific scope. However, it does not explicitly describe that it is a dispatcher for these sub-actions, which slightly affects clarity.

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 sibling tools like nucleus_agents or nucleus_audit. The description lists actions but does not provide conditions for choosing this tool or its sub-actions over 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?

Annotations provide no hints (readOnlyHint=false, destructiveHint=false). The description lists actions like 'close_commitment' and 'archive_stale' which imply side effects, but does not disclose behavioral details such as required permissions, idempotency, or consequences of actions. 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 structured as a bullet list with action names and parameter hints, which aids scanning. However, it is verbose due to the many sub-actions and could be shortened. The front-loaded summary line is good, but the list dominates.

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 an output schema (not shown), the description does not mention return values or behavior for each action. It lacks information on how to interpret results, error handling, or action-specific success conditions. For a tool with many sub-actions, this 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?

The input schema is minimal (action string, params object) with 0% parameter description coverage. However, the description lists each sub-action and its informal parameters (e.g., 'params: {detail_level?}', 'params: {commitment_id, method}'). This adds meaningful context beyond the bare schema, partially compensating for the lack of formal definitions.

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 lists many sub-actions under a broad header 'Satellite view, commitments, loops, patterns & metrics.' It gives a general sense of orchestration activities but lacks a specific verb-resource description for the tool as a whole. The purpose is vague and not clearly differentiated from 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?

No guidance is provided on when to use this tool versus the many sibling tools. There are no context trigger, prerequisites, or alternative tool mentions. The agent must guess usage from the action list 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?

The description discloses behavioral traits beyond annotations, such as auto-fill of sender and role, bearer token resolution without exposing secrets, and return formats. No contradiction with annotations (readOnlyHint false, destructiveHint false, openWorldHint true).

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

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

The description is well-structured with clear action headings and detailed parameter lists. It is slightly verbose but every sentence adds value. Could be more concise, but front-loads the main 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?

Given the complexity (4 actions, many optional parameters, security details), the description is extremely complete. It covers all actions, parameters, return values, and security configuration. The output schema exists and is described, so return values are 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?

The input schema has only two generic parameters (action, params) with 0% description coverage. The description compensates fully by detailing all possible parameters for each action (e.g., to, subject, body, sender?), including optional fields and aliases, making the tool usable.

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

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

The description clearly states it is a 'Relay-substrate facade — post / read / ack / status' and lists each action with specific verbs and resources. It distinguishes from sibling tools like nucleus_relay_subscribe by focusing on core relay operations.

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 this tool (relay operations) and lists all actions. However, it does not explicitly exclude alternatives or mention when to use sibling tools like nucleus_relay_subscribe, leaving some ambiguity.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds context about the subscription holding, polling replacement, and role detection bypass. It does not contradict annotations and provides behavioral context beyond them.

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

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

The description is front-loaded with purpose, then usage, then parameter details. It is slightly verbose but every sentence adds value. Could be tightened but overall 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?

Given the complexity (long-poll, role detection, inbox filter) and the presence of annotations and output schema, the description covers all necessary behavioral and usage aspects. It also includes background references (PR #1, HARD RULE) for full 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 coverage is 100%, but the description adds value: for inbox_filter it explains bypassing role detection and recommends for SessionStart hook; for timeout_seconds it ties to FastMCP TTL; for role it mentions default detection. Enhances understanding beyond schema.

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

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

The description clearly states it's a 'Long-poll subscription that pushes ctx.info() on each new inbox file.' The verb-subscribe and resource-inbox file arrival are specific. It distinguishes from sibling tools like nucleus_relay by mentioning it replaces bash polling daemons.

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 explicit when-to-use guidance: 'Call once at session start (e.g. via SessionStart hook)' and 'Use when role detection is unreliable OR when subscribing to a specific canonical inbox.' It implies a loop for persistence but does not explicitly list alternatives for when not to use.

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

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

Annotations already provide readOnlyHint=true and destructiveHint=false. The description adds behavioral context by specifying the return structure (provider, model, cost estimates, sovereignty tier) and the complexity parameter enum. No contradictions with 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 concise and front-loaded with the core purpose. It uses a structured list to present parameters efficiently, with no 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?

The description covers the main 'route' action adequately, but there is no mention of other possible actions (given the generic action parameter). The output schema is hinted at but not fully described. More detail 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?

With schema coverage at 0%, the description compensates by detailing the sub-parameters of the 'route' action (prompt, complexity, context, estimated_output_tokens). However, it only documents one action, leaving other potential actions undocumented.

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 'route a prompt to the optimal model tier' and provides a specific example action 'route' with its parameters. The tool name and title align, and the purpose is distinct from sibling tools like nucleus_agents and nucleus_audit.

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 routing a prompt to the cheapest capable model, but it does not provide explicit guidance on when to use this tool versus alternatives, nor does it mention 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?

Annotations are minimal (readOnlyHint=false, destructiveHint=false), so the description bears more responsibility. While the action names imply behavior (e.g., 'save' is a write, 'list' is read), the description does not disclose side effects, required permissions, or error behaviors. The per-action comments like 'Mandatory session start protocol' provide some transparency but overall 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 begins with a clear one-sentence summary, which is good. However, the subsequent list of 20+ sub-actions is lengthy and somewhat repetitive. It could be condensed by grouping similar actions or using bullet points. The structure is clear but not minimal; it earns its space but is verbose.

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 (many sub-actions, nested params, 15+ siblings), the description covers actions and their parameters well. However, it omits return values (even though an output schema exists), error conditions, and practical usage context for each sub-action. For a dispatcher tool, more guidance on action interactions would be beneficial.

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 is bare (only action and params with no descriptions), and schema description coverage is 0%. The description compensates by listing each action's expected parameter keys (e.g., for save: context, active_task?, etc.). This adds significant meaning beyond the schema, helping the agent know what to include. However, it does not specify types or constraints within those nested objects.

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 title 'Session Management' and the opening line 'Session management, events, state & checkpoint tools.' clearly indicate the tool's domain. The detailed list of sub-actions (save, resume, list, etc.) provides specific verbs and resources, distinguishing it from siblings like nucleus_tasks or nucleus_agents. However, the primary purpose is somewhat buried in a long list; a single concise sentence would improve clarity.

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 explicit when-to-use or when-not-to-use guidance is provided. The description is purely a list of sub-actions without explaining in what scenarios to prefer this tool over its siblings (e.g., nucleus_tasks for task-specific operations). An agent would have to infer usage from the action names alone, which is insufficient.

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

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

Annotations indicate it is not read-only and not necessarily destructive. The description lists mutating actions (e.g., slot_complete, force_assign) but does not disclose side effects, permission requirements, rate limits, or whether operations are reversible. It adds little behavioral context beyond the action names.

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

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

The description is dense and lengthy, listing all actions with parameters in a pseudo-bullet format. While structured, it is verbose and could be more concise by grouping or abbreviating redundant information. Still, it is organized and readable.

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

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

The description covers all actions and their parameters, but lacks context on return values (despite an output schema being present), error handling, workflow sequencing, and when to prefer this tool over siblings. For a complex multi-action tool, more contextual guidance would be beneficial.

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 0% description coverage, so the description fully compensates by enumerating each action's parameters with names, optional indicators (?), and brief descriptions (e.g., 'THE GOD COMMAND'). This provides complete semantic meaning that the schema lacks.

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 tool is for 'Orchestration slots, sprints & mission management.' This gives a clear domain. The list of actions further clarifies specific capabilities. However, it does not explicitly distinguish from sibling tools like nucleus_orchestration or nucleus_tasks, relying on the action names to imply 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 explicit guidance on when to use this tool versus alternatives. The description lists actions but does not state prerequisites, exclusions, or comparative advantages over sibling tools. An agent would have to infer usage from action names 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?

Annotations are minimal (readOnlyHint=false, destructiveHint=false), and the description adds little behavioral context. Many sub-actions imply state changes (e.g., write_artifact, trigger_agent), but the description does not disclose side effects, authorization requirements, or safety considerations.

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 excessively long (30+ lines) and poorly structured as a monolithic list. It lacks an executive summary or categorization, making it difficult for an agent to quickly grasp the tool's capabilities.

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 enumerates many sub-actions, it fails to cover usage context, error handling, return value interpretation (despite an output schema), or integration with siblings. The tool's complexity demands richer guidance than a mere list.

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

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

Despite 0% schema description coverage, the description embeds parameter hints for specific sub-actions (e.g., identify_agent, resolve_deploy), partially compensating for the generic {action, params} schema. However, many sub-actions lack detail, and the open-ended params object remains vague.

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 title 'Cross-Agent Sync' suggests synchronization, but the description covers a wide range of unrelated features including artifacts, triggers, deploy, relay, and marketplace operations. This diffuseness obscures the core purpose and fails to distinguish nucleus_sync from sibling tools like nucleus_relay or nucleus_federation.

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 simply enumerates sub-actions without explaining the overall use case, prerequisites, or conditions that would lead an agent to select nucleus_sync over other 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 lists actions like 'claim', 'update', 'add', 'import_jsonl' which are clearly mutating, but it does not explicitly disclose side effects, destructive potential, or permission requirements. The annotations (readOnlyHint=false, destructiveHint=false) are not contradicted but the description could add more behavioral context.

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

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

The description is well-organized with a clear title and bullet-like action list, but it is lengthy (17 actions). The most important information (action names and parameters) is front-loaded, though some repetition could be trimmed.

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 (multiple sub-actions) and the generic input schema, the description thoroughly enumerates all actions and their parameters. It does not cover return values or error conditions, but the presence of an output schema likely fills that gap. Overall, it provides sufficient context for an agent to select and invoke the right action.

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 is generic (action + params object with additionalProperties:true), so the description compensates by fully detailing each action's parameters (e.g., 'list - params: {status?, priority?, skill?, claimed_by?}'), which is essential for correct invocation. Schema coverage is 0%, making this description critical.

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 'Task management, depth tracking & ADHD context-switch tools,' providing a specific verb-resource combination that distinguishes it from sibling tools like nucleus_agents or nucleus_audit.

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 lists many actions with their purposes, implying when to use the tool for task, depth, or context-switch operations. While it does not explicitly compare with siblings, the tool's domain is clear and distinct from the sibling tools.

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

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

Annotations indicate readOnlyHint=false and destructiveHint=false, and the description mentions mutation actions like record_interaction, but it does not disclose side effects, authorization requirements, rate limits, or error handling beyond the action names.

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 structured as a bullet list with actions and brief descriptions, making it easy to scan. The initial sentence provides a high-level summary. However, the list is long and could be condensed by grouping similar actions.

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 (many actions, nested objects in output schema) and lack of structured parameter descriptions, the description is incomplete. It does not explain return values, error conditions, or action dependencies, leaving an agent underinformed.

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 no descriptions (0% coverage) and the description only lists parameter names for some actions (e.g., {tier}, {notification_type, score}) without types, formats, or defaults. This is insufficient for an agent to construct valid 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 opens with a clear summary 'LLM tiers, telemetry, PEFS notifications & protocol tools' and lists specific actions, which collectively define the tool's domain. However, the purpose could be more explicitly stated as a single coherent function rather than a collection.

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 sibling tools such as nucleus_governance or nucleus_agents. The description simply enumerates actions without context for selection.

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