The endiagram server performs deterministic, graph-theoretic structural analysis of systems modeled in EN (Entity-Node) syntax — no AI inside the computation.
analyze_system — Compute structural facts (shape, stages, bridges, cycles, actors, locations); optionally check invariants and detect antipatterns (unguarded-sinks, single/multi-cut-paths), liveness, boundedness, siphons, and traps.
render — Generate publication-quality SVG diagrams with configurable light/dark themes.
detail — Deep structural analysis: concurrency, flow landmarks, resilience metrics, dominator trees, and min-cuts.
distance — Find the shortest path between two nodes, annotated with subsystem crossings.
trace — Follow directed flow from node A to node B with role/subsystem annotations and optional defense-node highlighting.
diff — Structurally compare two systems, identifying topology, role, and subsystem changes.
extract — Extract a named subsystem as standalone EN source code.
impact — Blast-radius analysis: remove a node and see what disconnects.
evolve — Dry-run architectural changes by applying a patch and viewing the structural delta.
between — Compute betweenness centrality for a specific node (fraction of shortest paths through it).
categorize — Auto-discover subsystem boundaries from the dependency structure.
compose — Merge two EN graphs into one with explicit entity linking.
Allows rendering complex system dependency graphs and structural analysis results into publication-quality SVG images.
MCP server for EN Diagram — deterministic structural analysis powered by graph theory. Every result is backed by a named mathematical theorem. No AI inside the computation.
Run directly:
npx @endiagram/mcpOr install globally:
npm install -g @endiagram/mcpRelated MCP server: systems-thinking-mcp
claude mcp add endiagram npx @endiagram/mcpAdd to your claude_desktop_config.json:
{
"mcpServers": {
"endiagram": {
"command": "npx",
"args": ["@endiagram/mcp"]
}
}
}Add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"endiagram": {
"command": "npx",
"args": ["@endiagram/mcp"]
}
}
}Any MCP client that supports HTTP transport:
https://api.endiagram.com/mcpsmithery mcp add dushyant30suthar/endiagramVariable | Default | Description |
|
| API endpoint for the EN Diagram service |
Six questions about any system, plus a render tool. Every tool takes source (EN code or .en/.txt file path). Tool names are shorthand, not specs — read each description before calling; compose and equivalent are mode-based, not general analyzers.
Tool | What it answers | Levers |
| What is this system? Shape, stages, bridges, cycles, critical path, dominator tree, min-cuts, subsystems, actors, locations. |
|
| What's always true? Conservation laws, T-invariants (sustainable cycles), depletable sets, deficiency, reversibility. |
|
| Can it deadlock? Can entities overflow? Siphons, traps, unbounded cycles, structural liveness and boundedness. | — |
| Can X reach Y? Path, distance, boundary crossings. |
|
| Are two systems the same, or what changes if I change this one? | Compare mode ( |
| How do parts combine (merge) or how does a part stand alone (extract)? | Merge: |
| SVG or PNG diagram. Only call when the user asks to visualize. | Themes: |
One statement per line:
actor do: action needs: input1, input2 yields: output1, output2Shared names between yields and needs create connections automatically:
customer do: place order needs: menu yields: order
kitchen do: prepare food needs: order yields: meal
waiter do: deliver needs: meal yields: served customerSame name = same thing. Put all required inputs in one needs: list (AND). Give two actions the same yield-name to offer alternatives (OR). Sequence = one action consuming another's yield. Re-yield stateful resources to keep them persistent; one-shot data stays consumed. Model at the real atomic granularity — split only when the pieces could be accessed independently.
Learn more at endiagram.com.
@endiagram/mcp generates a random install ID on first run, stored at
~/.endiagram/install-id (mode 0600). It is sent with every request as
the X-Endiagram-Install-Id HTTP header so we can correlate requests
from the same install for debugging issues that the per-IP signal alone
cannot track (mobile networks, VPNs, CGNAT all collapse or churn IPs).
No source code, no file paths, no environment variables, and no PII are sent. The install ID is a random opaque UUIDv4 generated locally.
A first-run notice prints to stderr (never stdout — stdout is the MCP JSON-RPC channel) with the disclosure and the opt-out instructions. The notice fires once per install and never again.
Any of these three methods disables the install ID:
Set ENDIAGRAM_TELEMETRY=off as an environment variable (also
accepts 0, false, no).
Create a file at ~/.endiagram/telemetry containing the word off.
Delete ~/.endiagram/install-id. (A new one is generated on next
run unless option 1 or 2 is also set.)
When any of these is active, the X-Endiagram-Install-Id header is not
sent at all — the server falls back to its per-IP HMAC cid for
correlation, which works fine for short-term per-session tracing.
Full privacy policy: endiagram.com/privacy
MIT
Structural signal. You describe the system, the tool computes structural facts. All computation is deterministic — no AI inside. EN syntax: subject do: action needs: inputs yields: outputs.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | EN source code describing the system | |
| invariants | No | Invariants to check against the structure | |
| detect_antipatterns | No | Antipatterns to detect in the structure |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It states computation is 'deterministic' and 'no AI inside', which adds some behavioral context. However, it doesn't disclose critical traits like whether this is a read-only operation, what happens with invalid inputs, performance characteristics, or error handling. The description is insufficient for a tool with 3 parameters and no output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is relatively concise but poorly structured. The 'EN syntax' note is confusing and doesn't add value. The sentences are somewhat disjointed ('Structural signal.' stands alone awkwardly). While brief, the phrasing could be more coherent and front-loaded with clearer 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 3 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what 'structural facts' are computed, what format they're returned in, or how the parameters interact. For a tool that analyzes systems with multiple configuration options, more context about the analysis scope and results 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?
Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds no specific parameter information beyond what's in the schema. It mentions 'inputs' generically but doesn't clarify the meaning or relationships between 'source', 'invariants', and 'detect_antipatterns' 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 states the tool 'computes structural facts' from a system description, which gives a vague purpose. It mentions 'structural signal' and 'deterministic computation' but doesn't clearly specify what kind of facts or what 'structural' means in this context. It distinguishes from siblings by mentioning 'no AI inside', but the core function remains ambiguous.
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 like 'categorize', 'detail', or 'extract' from the sibling list. It mentions 'EN syntax' but doesn't explain when this tool is appropriate or what problems it solves compared to other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Betweenness centrality for a node — what fraction of all shortest paths flow through it.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | EN source code describing the system | |
| node | Yes | Node to compute betweenness centrality for |
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 explains the computation but lacks behavioral details such as performance characteristics (e.g., computational complexity for large graphs), error handling, or output format. This is a significant gap 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?
The description is a single, efficient sentence that directly states the tool's purpose and metric explanation. It is front-loaded with the core function and wastes no words, 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?
Given no annotations and no output schema, the description is minimal but covers the basic purpose. For a tool with 2 parameters and 100% schema coverage, it's adequate but lacks details on behavior and output, leaving gaps in completeness for effective agent use.
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 schema already documents both parameters ('source' and 'node'). The description adds no additional meaning about parameters beyond what the schema provides, such as format examples or constraints, meeting the baseline for high 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 computes 'betweenness centrality for a node' and explains the metric ('what fraction of all shortest paths flow through it'), which is specific and informative. However, it doesn't explicitly distinguish this from sibling tools like 'distance' or 'trace' that might also involve path analysis, missing full differentiation.
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. With siblings like 'distance', 'trace', and 'analyze_system' that might involve graph or path analysis, there's no indication of context, prerequisites, or exclusions for using 'between'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Auto-discover subsystem boundaries from dependency structure.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | EN source code describing the system |
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 'Auto-discover' but doesn't explain how the discovery works, what output to expect, whether it's read-only or mutating, performance characteristics, or error handling. This leaves significant gaps for a tool that analyzes system structure.
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, efficient sentence that directly states the tool's function without unnecessary words. It's front-loaded with the core purpose ('Auto-discover subsystem boundaries') and provides essential context ('from dependency structure') in a compact form.
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 that analyzes system dependencies with no annotations and no output schema, the description is insufficient. It doesn't explain what 'subsystem boundaries' means in practice, what format the results take, or how the dependency structure is processed. Given the complexity implied by terms like 'subsystem' and 'dependency structure', more contextual information 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?
Schema description coverage is 100%, with the single parameter 'source' documented as 'EN source code describing the system'. The description adds no additional parameter context beyond what the schema provides, such as format requirements or examples. With high schema coverage and only one parameter, 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 purpose with a specific verb ('Auto-discover') and resource ('subsystem boundaries'), explaining it analyzes dependency structure. However, it doesn't explicitly differentiate from sibling tools like 'analyze_system' or 'extract', which might have overlapping analysis functions.
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. With multiple sibling tools like 'analyze_system', 'detail', and 'extract' that might handle system analysis, the description lacks context about prerequisites, appropriate scenarios, or exclusions for this categorization function.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Merge two EN graphs into one with entity linking.
| Name | Required | Description | Default |
|---|---|---|---|
| source_a | Yes | EN source code for the first system | |
| source_b | Yes | EN source code for the second system | |
| links | Yes | Entity links between the two systems (e.g. 'a.node1=b.node2, a.node3=b.node4') |
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 the tool merges graphs with entity linking, implying a write or transformation operation, but doesn't detail what 'merge' entails—e.g., whether it creates a new graph, modifies inputs, or handles conflicts. It also omits information on permissions, rate limits, or error conditions, which are critical for a tool that likely performs complex graph operations.
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, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded with the core action ('Merge two EN graphs') and includes the key detail ('with entity linking'), making it easy to parse and understand 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 complexity of merging graphs with entity linking, the description is insufficient. With no annotations and no output schema, it fails to explain what the merged result looks like, how entity linking affects the output, or any behavioral traits like error handling. For a tool with three required parameters and no structured safety or output information, more descriptive context is needed to guide effective use.
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 each parameter clearly documented in the input schema (e.g., 'source_a' as 'EN source code for the first system'). The description adds minimal value beyond this, only implying that parameters relate to merging and linking without providing additional syntax or format details. This meets the baseline for 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 action ('Merge') and the resources ('two EN graphs'), specifying that entity linking is involved. It distinguishes itself from siblings like 'diff' or 'analyze_system' by focusing on combination rather than comparison or analysis. However, it doesn't explicitly differentiate from potential similar tools like 'evolve' or 'trace', which might also involve graph 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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, such as needing valid EN source code, or specify scenarios where merging is appropriate compared to using other tools like 'diff' for comparison or 'analyze_system' for inspection. This lack of context leaves the agent without clear usage instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Deep structural analysis — concurrency, flow landmarks, resilience, dominator tree, min-cuts.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | EN source code describing the system |
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 hints at analysis outputs (e.g., concurrency, resilience) but doesn't describe what the tool actually does behaviorally—such as whether it performs computation, returns data, modifies state, or has side effects. This leaves critical behavioral traits unspecified.
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—a single phrase listing analysis aspects—with no wasted words. However, it lacks front-loaded clarity (e.g., starting with a clear verb) and structure, making it somewhat cryptic rather than efficiently informative.
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 implied by terms like 'deep structural analysis' and the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns, how the analysis is performed, or the scope of results, leaving significant gaps for an agent to understand the tool's 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 description coverage is 100%, with the parameter 'source' documented as 'EN source code describing the system'. The description adds no additional meaning about parameters beyond what the schema provides, such as format details or examples. With high schema coverage, 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 lists technical analysis aspects (concurrency, flow landmarks, resilience, dominator tree, min-cuts) which gives a general sense of purpose, but it's vague about what specific action is performed. It doesn't clearly state a verb+resource combination like 'analyze source code for structural properties' or distinguish itself from sibling tools like 'analyze_system' or 'trace'.
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 doesn't mention prerequisites, context, or exclusions, and it doesn't reference any sibling tools like 'analyze_system' or 'trace' that might serve similar purposes, leaving the agent with no usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Structural diff between two systems — topology, role, and subsystem changes.
| Name | Required | Description | Default |
|---|---|---|---|
| source_a | Yes | EN source code for the first system | |
| source_b | Yes | EN source code for the second system |
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 states the tool performs a 'structural diff' but doesn't explain what that entails—whether it's read-only, what format the output takes, if there are rate limits, or any side effects. This leaves significant gaps in understanding the tool's 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 a single, efficient sentence that front-loads the core purpose ('Structural diff between two systems') and adds specific details ('topology, role, and subsystem changes') without unnecessary elaboration. 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 complexity of comparing two systems and the lack of annotations and output schema, the description is incomplete. It doesn't explain what a 'structural diff' outputs, how to interpret results, or any behavioral traits, making it inadequate for an agent to use the tool effectively without further 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 description coverage is 100%, with clear descriptions for both parameters ('EN source code for the first/second system'). The description adds no additional parameter semantics beyond what the schema provides, so it meets the baseline score for high schema coverage without adding value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs a 'structural diff' between two systems, specifying it examines 'topology, role, and subsystem changes.' This provides a specific verb ('diff') and resource ('two systems'), though it doesn't explicitly differentiate from sibling tools like 'analyze_system' or 'distance' that might also compare systems.
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 doesn't mention prerequisites, context for usage, or exclusions, leaving the agent to infer based on the tool name and parameters alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Shortest path between two nodes with subsystem crossing annotations.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | EN source code describing the system | |
| from | Yes | Starting node name | |
| to | Yes | Target node name |
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. While it mentions 'subsystem crossing annotations', it doesn't explain what this means operationally—whether this affects performance, requires specific permissions, has rate limits, or what the output looks like. For a path-finding tool with no annotation coverage, this leaves significant gaps in understanding how it behaves.
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, efficient sentence that states the core purpose without any fluff. It's appropriately sized and front-loaded, with every word contributing to understanding the tool's function. No wasted words or unnecessary elaboration.
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 of a path-finding tool with no annotations and no output schema, the description is insufficient. It doesn't explain what 'subsystem crossing annotations' means, what format the output takes, whether there are performance considerations, or how it differs from sibling tools. For a tool that likely returns structured path data, more context is needed to use it effectively.
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 schema already documents all three parameters (source, from, to) with clear descriptions. The description adds no additional meaning about these parameters beyond what's in the schema. It mentions 'subsystem crossing annotations' which might relate to the 'source' parameter, but this is vague and doesn't enhance parameter understanding. Baseline 3 is appropriate when 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's purpose: 'Shortest path between two nodes with subsystem crossing annotations.' It specifies the action (finding shortest path) and the resource (nodes with subsystem annotations). However, it doesn't distinguish this from sibling tools like 'trace' or 'between' that might also involve path-related operations, so it doesn't reach the highest 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?
The description provides no guidance on when to use this tool versus alternatives. With sibling tools like 'trace', 'between', and 'analyze_system' that might involve similar path or relationship analysis, there's no indication of what makes 'distance' unique or when it's the appropriate choice. The description only states what it does, not when to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Dry-run architectural changes — apply a patch and see the structural delta.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | EN source code describing the current system | |
| patch | Yes | EN source code patch to apply |
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 states this is a 'dry-run' operation, implying it's non-destructive and read-only, which is helpful. However, it doesn't describe other behavioral traits such as performance characteristics, error handling, or what 'structural delta' entails in terms of output format. For a tool with no annotations, this is a significant gap in 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 highly concise and front-loaded, consisting of a single sentence that efficiently conveys the core functionality: 'Dry-run architectural changes — apply a patch and see the structural delta.' Every word earns its place, with no unnecessary elaboration, making it easy 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 complexity of architectural changes and the lack of annotations and output schema, the description is incomplete. It doesn't explain what 'structural delta' means in practice, how results are presented, or any limitations (e.g., supported patch formats). For a tool with no structured output and behavioral gaps, this leaves the agent with insufficient context to use it effectively.
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% description coverage, with clear documentation for both parameters ('source' and 'patch'). The description adds minimal value beyond the schema, as it doesn't explain parameter semantics like what 'EN source code' means or how the patch should be formatted. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, but the description could have enhanced understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Dry-run architectural changes — apply a patch and see the structural delta.' It specifies the verb ('dry-run'), resource ('architectural changes'), and outcome ('see the structural delta'), making it easy to understand what the tool does. However, it doesn't explicitly differentiate from sibling tools like 'diff' or 'analyze_system', which might 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 minimal guidance on when to use this tool, only implying it's for previewing changes before applying them. It doesn't specify when to use it versus alternatives like 'diff' (which might compare differences) or 'analyze_system' (which might assess impacts), nor does it mention prerequisites or exclusions. This leaves the agent with little context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Extract a named subsystem as standalone EN source code.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | EN source code describing the system | |
| subsystem | Yes | Name of the subsystem to extract |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. While 'extract' implies a read operation, it doesn't disclose whether this modifies the source, requires specific permissions, has rate limits, or what happens if extraction fails. For a tool that presumably transforms source code, this lack of behavioral context is significant.
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, efficient sentence with zero wasted words. It's appropriately sized and front-loaded with the core purpose, making it easy for an agent to quickly understand what the tool does.
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 apparent complexity (extracting subsystems from source code), lack of annotations, and no output schema, the description is minimally adequate. It states what the tool does but doesn't provide enough context about behavior, output format, or usage scenarios to be truly complete for this type of operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description doesn't add any meaning beyond what the schema provides about 'source' and 'subsystem' parameters. The baseline of 3 is appropriate when 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 action ('extract') and the target ('named subsystem as standalone EN source code'), providing a specific verb+resource combination. However, it doesn't differentiate this tool from its many siblings (like 'analyze_system', 'compose', 'detail', etc.), which appear to operate on similar EN source code systems.
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. With 11 sibling tools that likely work with EN source code systems, there's no indication of what problem this tool solves that others don't, nor any prerequisites or context for when extraction is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Blast radius — remove a node and see what disconnects.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | EN source code describing the system | |
| node | Yes | Node to remove for impact analysis |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It states the tool removes a node for impact analysis, implying a destructive or simulation operation, but doesn't disclose whether this is a real removal, simulation, permission requirements, rate limits, or output format. The phrase 'blast radius' suggests destructive impact but lacks clarity on actual 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 (one sentence) and front-loaded with the core purpose. Every word earns its place with no wasted text, 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 no annotations and no output schema, the description is incomplete. It doesn't explain what 'disconnects' means in the output, whether this is a simulation or actual change, error conditions, or how results are presented. Given the complexity implied by 'blast radius' analysis, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters ('source' and 'node'). The description implies these parameters are used for impact analysis but doesn't add meaningful semantics beyond what the schema provides (e.g., format examples or constraints). Baseline 3 is appropriate given 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 performs impact analysis by removing a node to see what disconnects. It specifies the verb ('remove a node and see what disconnects') and resource ('node'), but doesn't explicitly differentiate from siblings like 'analyze_system' or 'trace' which might 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 like 'analyze_system' or 'trace'. It mentions the action but doesn't specify prerequisites, constraints, or comparative context with sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Render an EN dependency graph as a publication-quality SVG image.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | EN source code describing the system | |
| theme | No | Color theme for the rendered image | |
| quality | No | Output quality / resolution |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions the output is 'publication-quality' but doesn't disclose behavioral traits like processing time, file size implications, error handling for invalid source, or whether it's a read-only operation. This leaves significant gaps for a tool that generates images.
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, efficient sentence with zero waste. It's front-loaded with the core purpose and avoids unnecessary details, making it easy to scan and understand 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 no annotations and no output schema, the description is minimal but covers the basic purpose. However, for a tool with 3 parameters that generates visual output, it lacks details on output format specifics, error conditions, or performance considerations, making it only adequate for simple use cases.
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 schema already documents all parameters thoroughly. The description adds no meaning beyond what the schema provides, such as explaining how 'source' should be formatted or what 'publication-quality' entails in terms of 'quality' settings. Baseline 3 is appropriate when 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 specific action ('render'), the resource ('EN dependency graph'), and the output format ('publication-quality SVG image'). It distinguishes this tool from siblings like 'analyze_system' or 'trace' by focusing on visualization rather than analysis or tracing.
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 like 'compose' or 'evolve'. It doesn't mention prerequisites, such as needing valid EN source code, or exclusions, like not being suitable for non-graph data.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Follow directed flow from node A to node B with role and subsystem annotations.
| Name | Required | Description | Default |
|---|---|---|---|
| source | Yes | EN source code describing the system | |
| from | Yes | Starting node name | |
| to | Yes | Target node name | |
| defense_nodes | No | Comma-separated list of defense nodes to annotate |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions 'role and subsystem annotations' but doesn't disclose behavioral traits such as what the tool returns (e.g., a path list, visualization), error handling, performance considerations, or if it modifies data. This leaves significant gaps in understanding how the tool behaves.
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, efficient sentence that front-loads the core action ('Follow directed flow'). It avoids redundancy but could be slightly more informative without losing conciseness, such as hinting at the output or use case.
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 and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., a trace result, annotations details), error conditions, or how it integrates with the system. For a tool with 4 parameters and complex tracing functionality, more context is needed to guide effective use.
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 parameters are well-documented in the schema. The description adds minimal value beyond the schema by implying parameters are used for tracing flows with annotations, but it doesn't provide additional context like format examples or interdependencies. Baseline 3 is appropriate 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 states the tool 'follow[s] directed flow from node A to node B with role and subsystem annotations,' which clarifies it traces a path between nodes in a system. However, it's vague about what 'directed flow' entails (e.g., data flow, control flow) and doesn't differentiate from siblings like 'between' or 'distance,' which might have similar functions.
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 implies it's for tracing flows with annotations, but it doesn't specify contexts, prerequisites, or exclusions, nor does it compare to sibling tools like 'between' or 'distance' that might handle related tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.4analyze_systembetweencategorizecomposedetaildiffdistanceevolveextractimpactrendertraceScored across 12 tools
Most tools target distinct graph operations, but trace, distance, and between all revolve around paths and centrality, while analyze_system, detail, and categorize overlap in structural analysis. Descriptions help but an agent could reasonably pick the wrong tool for some analytical tasks.
Tool names are mostly single lowercase words, but they mix verbs, nouns, and prepositions (between, distance, impact, detail), and analyze_system breaks the pattern with snake_case. There is no consistent verb_noun or predictable naming convention.
Twelve tools is well-scoped for a dependency-graph analysis server. Each tool has a recognizable responsibility within analysis, rendering, transformation, and composition, without feeling padded or thin.
The toolkit covers traversal, centrality, structural diffing, subsystem discovery, deep analysis, rendering, merging, and dry-run evolution. Minor gaps like explicit node creation/deletion or cycle detection exist, but the server's analytical focus is well covered.
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
End-to-end agent-managed company brain. Docs, diagrams, plans, Knowledge Graph. Lean & affordable.
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
