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

With no annotations, the description carries the burden of behavioral disclosure. It reveals that the tool handles layout, styling, and rendering automatically for graph types, that specs accept title/subtitle and focal elements, and that marking five focal elements erases the effect. It does not mention file overwrite behavior or permissions, but the creation semantics and return expectations are reasonably transparent.

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

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

The description is front-loaded with the core purpose and then uses two clearly labeled bullets for input modes. It is compact, well-structured, and every sentence contributes either to mode selection or to the required discovery workflow.

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 7 parameters, no annotations, and an available output schema, the description is complete enough to guide correct invocation. It identifies required payloads per mode, points to the type-list and schema tools for dynamic discovery, and leaves return-value concerns to the output schema.

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

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

Schema coverage is 100%, so the baseline is 3; the description adds value by framing the conditional parameter groups (nodes+connections for graph types, diagram_type+spec for typed diagrams) and explaining what the agent must supply before calling. This mode-conditional interpretation is not as obvious from the schema alone.

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 opening sentence names a specific verb and resource: 'Create a new Excalidraw diagram of any supported type.' The two-mode breakdown (graph types vs typed diagrams) makes the scope precise and distinguishes it from sibling operations like modify_diagram, export_diagram, and mermaid_to_excalidraw.

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 mode-selection guidance: pass nodes/connections for architecture/flowchart, or diagram_type+spec otherwise, and directs the agent to list_diagram_types and get_diagram_schema to fill in type-specific details. It does not explicitly contrast with siblings like modify_diagram or mermaid_to_excalidraw, but the usage context for this tool is clear.

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

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

No annotations are provided, so the description carries the burden. It mentions the conversion process and that no external app is needed, but does not disclose if the input file is modified, error handling, or permission requirements. Basic but not thorough.

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

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

Two concise sentences that front-load the core function. No excess words or redundancy.

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

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

With an output schema present, return values are assumed documented. The description covers the primary use case and parameters adequately. Slight missing detail about failure modes, but sufficient for a conversion 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?

Input schema covers all parameters with descriptions (100% coverage). The description adds minimal new information beyond the schema, mainly restating the purpose. Baseline 3 is appropriate.

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

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

The description clearly states the action (export), the resource format (.excalidraw), and the output formats (SVG/PNG). This distinguishes it from sibling tools like create_diagram or modify_diagram.

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

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

The description implies usage for generating portable images without browser/Excalidraw, but does not explicitly compare with siblings or state when not to use (e.g., for editing). It provides implicit context but lacks clear directives.

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

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

No annotations are provided, so the description carries the full burden. It discloses that the tool returns a summary with node ids, labels, component types, and connection topology. While it does not mention error conditions or permission needs, the read-only nature is implied and the output context is sufficient for a simple getter.

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 consists of two focused sentences. The first defines the core purpose, and the second provides usage guidance and output summary. Every word adds value with no redundancy or filler.

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

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

Given a single parameter, a clear output schema, and a simple getter operation, the description is fully adequate. It explains the purpose, usage context, and output contents. No critical information is missing for an agent to use the tool correctly.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds no additional parameter information beyond the schema's own description of 'file_path.' The description focuses on output rather than parameter details, so it does not enhance parameter 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 the verb 'Get' and resource 'structured summary of an existing Excalidraw diagram.' It explicitly names sibling tool 'modify_diagram' and frames the call as a prerequisite, distinguishing its role.

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

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

The description provides explicit guidance: 'Call this BEFORE modify_diagram to understand what nodes and connections currently exist.' This tells the agent exactly when and why to invoke the tool.

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

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

With no annotations, the description carries the full burden. It clearly indicates this is an informational retrieval operation via 'Get', states what is returned (JSON schema and selection guidance), and implies no side effects. It does not mention error or auth behavior, but for a simple schema-lookup tool the transparency is adequate.

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

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

The description is two sentences with no filler. The first sentence defines the tool's purpose, and the second provides actionable usage context. Every sentence earns its place, and the most important information is front-loaded.

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

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

With a single well-documented parameter and an output schema present, the description does not need to enumerate return fields. It gives the essential workflow context and names the relevant sibling tool. Nothing critical is missing for an agent to correctly select and invoke this tool.

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

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

Schema description coverage is 100%, and the diagram_type parameter already includes examples and a pointer to list_diagram_types. The tool description adds context about the parameter's role in constructing a spec but does not substantially extend the schema's parameter documentation. Baseline 3 is appropriate.

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

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

The description states a specific verb ('Get'), a clear resource ('JSON schema and selection guidance for one diagram type'), and scopes it to a single diagram type. This makes it easy to distinguish from siblings like list_diagram_types and create_diagram.

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 usage direction: call this before passing a spec to create_diagram for a type not yet used. It ties the tool to a concrete workflow and explains the benefit (payload matches on the first attempt), leaving no ambiguity about when to invoke it.

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

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

No annotations provided, so description carries full burden. It only says 'add or update' but does not disclose idempotency, merge behavior, side effects, permissions, or error handling. The mutation behavior is implied but not explained.

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

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

Single sentence, efficient and front-loaded with purpose. However, overly concise given tool complexity; could benefit from brief behavioral notes.

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?

Complex tool with 10 parameters and output schema not described. No information about return value, format, or what 'add or update' means for existing services. Given richness of schema, more context expected.

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

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

Schema coverage is 100%, so parameters are well-documented in schema. Description adds no extra meaning beyond the schema. Baseline 3 is appropriate.

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

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

Description clearly states 'Add or update a service in the knowledge graph.' The verb 'add or update' and resource 'service' are specific. Sibling tools include kg_remove_service, kg_link, etc., making the tool's role distinct.

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 vs alternatives. No mention of prerequisites, when not to use, or scenarios for adding vs updating. Sibling tools exist but are not referenced.

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

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

No annotations are provided, so the description must disclose behavior. It states that the tool compares the current file against a version at a git ref, implying a read-only operation. However, it does not explicitly confirm safety, permissions, or side effects. With an output schema present, the behavior is partially communicated.

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

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

Two sentences, both front-loaded with the key purpose and a clarifying follow-up. Every word adds value, no redundancy. The structure is optimal for quick parsing.

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 existence of an output schema (not shown but present), the description covers the core functionality. However, it lacks details on parameter roles, comparison scope, and when to use it over similar tools. For a tool with an output schema and many siblings, more context would help decision-making.

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

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

Schema description coverage is 0%, meaning the schema provides no explanations for parameters. The description does not elaborate on 'ref' or 'graph_path' beyond their defaults. It fails to add meaning or context for how these parameters affect the diff, leaving the agent to infer from defaults.

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: 'Show how the architecture changed since a git ref'. It specifies the resource (architecture) and action (show diff). While it doesn't explicitly differentiate from sibling tools like kg_drift, the git ref mechanism is distinct enough to imply its use case.

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

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

No guidance on when to use this tool versus alternatives such as kg_drift or kg_info. There is no mention of prerequisites, when not to use, or expected contexts. The description only mentions defaults but no usage scenarios.

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

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

With no annotations provided, the description must disclose all behavioral traits. It mentions 'best-effort' implying non-guaranteed correctness, and that it reports 'possibly-stale dependencies' and 'undocumented' edges. However, it does not disclose side effects, system modifications, required permissions, or the nature of the output beyond the mention of reports. The output schema exists but is not provided, so the description partially but incompletely covers 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 brief (two short paragraphs) with front-loaded purpose. The first sentence defines the tool, the second adds method details. No redundant information. It could be more structured but remains efficient.

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

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

Given the complexity of drift detection, the description explains the method (best-effort, treats top-level packages as services, infers edges) and what is reported (undocumented, possibly-stale dependencies). However, it does not explain prerequisites (e.g., existence of architecture file), output format (though output schema exists but not provided), or error handling. It is somewhat complete but leaves gaps.

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

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

The input schema has 0% description coverage, so the description must compensate. It provides context for code_root (directory to scan) and implicitly for graph_path (architecture file) via 'Detect drift between declared architecture and Python imports' and the default value. However, it does not explicitly link parameter names to their roles or describe the format expected. This is adequate but not excellent.

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 detects drift between declared architecture and Python imports, specifying the action ('detect'), the resource ('drift between declared architecture and Python imports'), and the scope ('under code_root'). This distinct purpose differentiates it from siblings like kg_diff (diff) and kg_lint (linting).

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 explains the method (best-effort, treats top-level packages as services, infers edges from imports) and what it reports (undocumented and possibly-stale dependencies), which helps understand usage context. However, it lacks explicit guidance on when to use this tool vs alternatives like kg_diff or kg_lint, and does not mention prerequisites or limitations.

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

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

With no annotations provided, the description must disclose behavioral traits, but it only says 'export,' which implies a non-destructive read. It does not mention whether the tool modifies the graph, handles errors, or has side effects, leaving significant gaps in understanding.

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), which is good for conciseness, but it sacrifices clarity and structure. It is front-loaded but lacks any supplementary details that would improve usability.

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 siblings, no annotations, 3 parameters), the description is incomplete. Although an output schema exists, the description does not explain the tool's role in a workflow, what triggers it, or how it relates to other knowledge graph tools.

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

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

The schema coverage is 67% (format and output_path have descriptions, graph_path is missing). The description adds no extra meaning about the parameters; it merely restates the tool's purpose. An agent must rely solely on the schema for parameter 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 states 'Export the knowledge graph to another format,' which clearly identifies the action (export) and resource (knowledge graph), but it is vague about what 'another format' entails. It distinguishes from siblings like kg_import and kg_render, but lacks specificity about the output formats, which are only detailed in the schema.

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 its many siblings (e.g., kg_import, kg_render, export_diagram). There is no mention of context, prerequisites, or alternatives, making it difficult for an AI agent to select appropriately.

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

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

No annotations are provided, so the description must cover behavioral aspects. It mentions importing services and bootstrapping but does not disclose side effects (e.g., overwriting existing data, error handling, or auth requirements).

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 (two sentences) with no wasted words. However, it could be slightly more informative without sacrificing conciseness.

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

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

Given the tool's complexity (importing a diagram into a knowledge graph), the description is incomplete. It does not explain what 'importing services' entails, what the output is, or potential error 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 coverage is 0%, but the description adds no meaning for the parameters (excalidraw_path, graph_path). It does not explain expected formats or how they affect behavior.

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 (import), the resource (existing .excalidraw diagram), and the target (knowledge graph). It distinguishes from sibling tools like create_diagram and export_diagram.

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

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

The phrase 'Bootstraps the graph from diagrams you already created with this tool' implies a specific use case, but it does not explicitly state when to use vs. alternatives or 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?

No annotations provided, so description carries full burden. Indicates a read operation ('summarize'), but lacks details on permissions, side effects, or output size. Adequate for a simple info tool.

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

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

Extremely concise with two sentences. Front-loaded with the main purpose, no wasted words.

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

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

Has an output schema (not shown), so description does not need to detail return values. Explains when to use and what it does, sufficient for a simple tool with one optional parameter.

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

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

Schema coverage is 0% with no description for 'graph_path'. The tool description does not mention the parameter, leaving its purpose and usage ambiguous. Does not add value 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?

Clearly states the verb 'summarize' and the resource 'knowledge graph', specifying aspects like services, domains, and topology. Differentiates from sibling tools like kg_add_service or kg_diff by indicating it's an overview tool.

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?

Explicitly advises calling this tool before mutations to reason about current state, providing clear context for use. Does not explicitly mention alternatives but gives a strong usage cue.

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

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

No annotations are provided, so the description carries the full burden. It mentions overwriting but does not disclose whether creation is destructive to existing files (beyond overwrite), side effects, or required permissions. Lacks details on concurrency or failure modes.

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 brief with two main sentences and a third about rendering. It is front-loaded with the primary action. The third sentence is mildly extraneous but does not detract.

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 what the tool returns or what happens after creation (e.g., confirmation, path). For a tool that creates a file, this is a notable gap.

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

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

The description adds no extra meaning beyond the input schema, which already covers all four parameters with descriptions. Schema coverage is 100%, so baseline 3 is appropriate.

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

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

The description clearly states the tool creates a new knowledge graph file (markdown) with a specific verb and resource. It distinguishes from siblings like kg_add_service (adds a service) and kg_lint (lints), which are different 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 implies that the knowledge graph is a persistent source of truth and that diagrams are rendered from it, but it does not explicitly state when to use this tool vs alternatives (e.g., kg_import for importing an existing graph) or when not to use overwrite.

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

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

No annotations present, so description must cover behavior. It states directed dependency and describes style parameter but does not disclose idempotency, error handling if link exists, or side effects.

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

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

Three short sentences, front-loaded with main action, efficient 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?

Covers core purpose and prerequisite but omits behavior on duplicates, return values (though output schema exists), and two parameters. Adequate but incomplete given 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?

Schema has 5 parameters with 0% description coverage; description only explains from_id, to_id, and style. Label and graph_path are not described, leaving gaps 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?

Clearly states the action 'Add a directed dependency' and specifies the resources 'from_id' and 'to_id'. Distinguishes from sibling tools like kg_add_service and kg_unlink by focusing on linking services.

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

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

Provides prerequisite: services must exist and points to kg_add_service. Gives usage context but does not explicitly mention when not to use or compare to alternatives.

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

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

With no annotations, the description must disclose behavioral traits. It lists what is checked but does not state whether the tool is read-only, modifies state, requires prerequisites, or has side effects. The lack of behavioral disclosure is a 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?

A single sentence that front-loads the purpose and lists specific checks. Every word earns its place; no extraneous content.

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

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

Given two parameters, no annotations, but an output schema exists, the description adequately explains what the tool does and what it checks. However, it misses details like output format or whether initialization is required, but overall it is fairly complete for a lint tool.

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

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

Schema coverage is 0%, so the description must compensate. It mentions 'optionally unowned services,' which maps to check_owners, but does not explain graph_path. Some meaning is added for one parameter, but graph_path remains undefined.

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 performs an 'Architecture health check' and lists specific issues (cycles, single points of failure, orphans, dangling references, unowned services). This verb+resource combination distinguishes it from sibling tools like kg_add_service or kg_render.

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 vs. alternatives like kg_drift or kg_diff. The description only implies usage for architecture health checking, but does not provide criteria or exclusions.

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

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

With no annotations provided, the description has full responsibility for behavioral disclosure. It implies a non-destructive read operation ('generate'), but does not explicitly state whether it modifies the graph, requires permissions, or has side effects. Minimal transparency leaves the agent guessing.

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

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

The description is a single sentence, but it is vague and omits critical information. It does not earn its place because it fails to convey how to use the tool effectively. True conciseness would include parameter context or usage hints.

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

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

Given the tool has 2 parameters with no schema descriptions and no annotations, the description is severely incomplete. It does not explain the parameters or the output format, and the presence of an output schema does not compensate for missing invocation guidance.

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

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

Schema description coverage is 0%, yet the description adds no explanation for the two parameters ('output_path' and 'graph_path'). Neither the purpose nor formatting of these parameters is clarified, leaving the agent without necessary invocation details.

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 ('Generate') and the resource ('human onboarding guide (entry points, hubs, domains) from the graph'). It distinguishes the tool's purpose from siblings like 'kg_render' or 'kg_lint', which focus on different outputs. However, it could explicitly differentiate from other kg tools that also generate content from the graph.

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

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

No guidance on when to use this tool versus alternatives. The description does not mention prerequisites, context, or when not to use it. Sibling tools like 'kg_render_domain' or 'kg_info' might overlap, but no comparison is provided.

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

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

Behavior is implied but not detailed: e.g., what happens if no path exists, how cycles are handled, or what format the path returns. No annotations exist to supplement.

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?

Extremely concise single sentence with no waste, but it sacrifices detail that could be added without expanding length.

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

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

Despite having an output schema, the description lacks context on ID types, graph_path default, and error handling. Incomplete for a tool with many siblings and no schema comments.

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 has 0% description coverage; description only hints at 'two services' (from_id, to_id) but does not explain graph_path or parameter formats beyond the schema defaults.

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

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

The description clearly states the verb 'Trace' and the resource 'shortest dependency path between two services', which distinguishes it from sibling tools like kg_link or kg_info.

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 vs alternatives such as kg_info or kg_render. No exclusion criteria or prerequisites mentioned.

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

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

No annotations are provided, so the description must disclose behavioral traits. It mentions the removal of dependencies, but lacks details on reversibility, side effects, permission requirements, or what happens to links. For a destructive tool, this is insufficient.

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

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

The description is very short (one sentence), which is concise, but it omits crucial information. It does not earn its place because it fails to add significant value beyond the tool name.

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

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

Given the destructive nature of the tool and the absence of annotations, the description is inadequate. It does not explain the output, the impact on dependencies, or any safety considerations. An output schema exists but no reference to it.

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

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

Schema description coverage is 0%, meaning no parameters are described in the schema. The description does not explain the 'id' or 'graph_path' parameters, their formats, or how they affect behavior. This fails to compensate for the lack of schema documentation.

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 (remove) and the target (service), and adds specificity by mentioning 'all dependencies touching it'. This distinguishes it from sibling tools like kg_add_service or kg_unlink.

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

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

The description implies usage for removing services, but provides no guidance on when to use it versus alternatives like kg_unlink, or any prerequisites or conditions. The context is implied, not explicit.

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

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

No annotations are provided, so the description must fully disclose behavior. It only states a high-level action without explaining what 'render' entails, whether it overwrites files, or any side effects. Does not mention the output schema or return 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 sentence, very concise, but it sacrifices necessary details. While front-loaded with the main action, it lacks parameter information and usage 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 has three parameters, no annotations, and many sibling tools for granular rendering, the description is incomplete. It does not explain the output format details, theme options, or graph_path usage. An output schema exists but is not referenced.

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

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

Schema description coverage is 0%, meaning the schema provides no parameter explanations. The description fails to add any meaning to the three parameters (output_path, theme, graph_path), leaving the agent unaware of acceptable values or defaults.

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 ('Render'), the resource ('entire architecture'), and the output format ('.excalidraw file'). It distinguishes from siblings like kg_render_around, kg_render_domain, and kg_render_view by specifying 'entire architecture'.

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 kg_render_view or kg_render_domain. No context about prerequisites or when not to use it.

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

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

No annotations provided, so description carries full burden. It mentions direction parameter but does not disclose side effects (e.g., file creation/modification), permissions, or return format. The output schema exists but description does not leverage it.

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 short and front-loaded with purpose. However, it could be more structured to include parameter summaries. Two sentences with backtick formatting are clean.

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 6 parameters (3 required) and an output schema, the description is too sparse. It does not explain how 'depth' and 'hops' work, nor the output behavior. Incomplete for a tool with moderate 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?

Schema coverage is 0% — the description only explains the 'direction' parameter values. Other 5 parameters (service_id, depth, output_path, theme, graph_path) are undefined. The description adds minimal meaning 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 the verb 'Render' and the resource 'a service plus everything within depth hops of it'. It distinguishes from similar siblings like kg_render (probably single service) and kg_render_domain.

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

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

The description implies usage for rendering a service and its neighbors, but does not provide explicit when-to-use or when-not-to-use guidance compared to siblings. No alternatives or exclusions mentioned.

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

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

No annotations provided. Description does not disclose behavioral traits (e.g., if rendering is read-only, output format, side effects). Minimal insight beyond the action.

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

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

Single short sentence is concise but lacks structure (e.g., no breakdown of parameters or usage flow). Acceptable for a simple tool but misses opportunity to add value.

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

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

With 4 parameters, no schema descriptions, no annotations, and many sibling tools, the description is far too sparse. Missing parameter details, behavioral info, and output 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 0%, yet description adds no parameter meaning. 'domain' and 'output_path' are required but unexplained; 'theme' and 'graph_path' are entirely opaque.

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?

Verb 'render' and resource 'services belonging to one domain' are specific. Clear distinction from siblings like 'kg_render' (likely all services) and 'kg_render_around'.

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?

Implicitly suggests use when only a subset (one domain) is needed, but no explicit when-to-use, when-not-to-use, or alternatives mentioned.

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

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

No annotations are provided, so the description carries full burden. It does not disclose side effects (e.g., file creation at output_path), authentication needs, rate limits, or whether the tool is read-only. The single sentence only describes the output, not 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, front-loaded sentence with no redundancy. It efficiently conveys the core purpose. However, it could be expanded slightly to improve completeness without losing conciseness.

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

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

Despite having an output schema (not shown), the description is insufficient for a 4-parameter tool with no annotations. Missing parameter details and usage context make it hard for an agent to invoke correctly.

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

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

Schema description coverage is 0%, meaning no parameter descriptions exist in the schema. The description adds minimal meaning: 'given services' hints at node_ids, but nothing about output_path, theme, or graph_path. Required parameter output_path is unexplained.

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

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

The description uses a specific verb 'Render' and identifies the resource as 'focused diagram of just the given services (induced subgraph)'. This clearly differentiates from sibling tools like kg_render (likely renders full graph) and kg_render_around (renders around a node).

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 like kg_render, kg_render_around, or create_diagram. The description only implies input via node_ids but does not explain when an induced subgraph is appropriate.

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

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

No annotations are provided, so the description must disclose behavioral traits. It does not mention side effects, permissions, overwriting behavior, or what happens to existing associations, leaving critical unknowns.

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

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

The description is a single sentence with no waste, but it is under-specification rather than conciseness. Important details are omitted, making it insufficiently 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 no annotations, 4 parameters, and an existing output schema, the description is extremely incomplete. It does not explain the return value or any behavioral consequences, leaving the agent with insufficient 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 0%. The description only hints at 'service', 'domain', and 'label', but fails to explain service_id format, graph_path purpose, or any constraints (e.g., domain string pattern). Four parameters are barely documented.

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: assigning a service to a domain, with an optional label. It is specific about the verb and resource, but does not differentiate from sibling tools like kg_link or kg_render_domain.

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 vs alternatives. There is no mention of prerequisites, context, or exclusions, leaving the agent without decision support.

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

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

With no annotations, the description must disclose behavioral traits. It only states removal without mentioning consequences, permissions, or side effects. The tool is likely destructive, but no context given.

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 no redundancy. However, it sacrifices completeness for brevity, earning a high conciseness score but low overall utility.

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 (modifying a knowledge graph) and the presence of an output schema, the description should explain the return format. It also ignores the graph_path parameter entirely. Inadequate for reliable invocation.

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

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

Schema description coverage is 0%. The description implicitly mentions from_id and to_id but does not explain their meaning or the optional graph_path parameter. Parameters are left to the schema alone.

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

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

The description explicitly states 'Remove the dependency' with a clear subject (from_id -> to_id). It is a specific verb+resource and distinguishes from sibling tools like 'kg_link' which adds dependencies.

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 vs alternatives like 'kg_link' or other kg_ tools. No prerequisites or exclusions provided.

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

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

No annotations are provided, so the description carries the full burden. It discloses return format ('A table of type -> family, when to use it, and when not to') and gives practical behavioral guidance about density and focal elements. It stops short of explicitly stating side-effect-free/read-only behavior, but 'List' strongly implies it.

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?

Front-loaded with purpose, followed by clear usage direction, helpful rules, and return format. The bullet points keep the guidance scannable, and every sentence adds value without redundancy.

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

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

For a zero-parameter listing tool, the description fully covers what the agent needs: what the tool returns, when to call it, and why it matters. The presence of an output schema means return values do not need further elaboration.

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 an empty object with zero parameters, so there is nothing to explain. With 0 params, the baseline is 4, and the description correctly avoids inventing parameter 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 has a specific verb and resource: 'List every supported diagram type with guidance on when to use it.' It clearly distinguishes this tool from siblings like create_diagram by focusing on exploration and selection guidance rather than creation or manipulation.

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?

Explicitly instructs to call this tool BEFORE create_diagram when the right diagram type isn't obvious. It also explains why (wrong type causes diagrams to fail) and provides two general rules for diagram creation, giving strong context for when and how to use the output.

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

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

No annotations are provided, so the description carries full burden. It discloses that component types are auto-detected from node labels (e.g., 'PostgreSQL DB' gets database styling), which is a key behavioral trait. It also lists supported directions, node shapes, edge types, and subgraphs, providing good transparency for a conversion tool.

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

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

The description is reasonably concise with three paragraphs. The main purpose is stated in the first sentence. Each section adds value, though the list of supported syntax could be slightly trimmed. Overall, it is well-structured and front-loaded.

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

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

Given the tool's complexity (converting Mermaid flowcharts to Excalidraw), the description covers the supported syntax, auto-detection behavior, and output path. An output schema exists, so return values need not be detailed. Minor omissions like error handling or file overwrite behavior do not significantly detract from 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?

The input schema already has 100% coverage and clear descriptions for all three parameters. The description adds value by explaining the supported Mermaid syntax subset and auto-detection, but this is not directly tied to individual parameter semantics. Thus a 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 converts Mermaid flowchart syntax to an Excalidraw diagram, specifying the verb 'Convert' and the resources 'Mermaid flowchart syntax' and 'Excalidraw diagram'. This distinguishes it from sibling tools that create, export, get info, or modify diagrams.

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 details the supported Mermaid subset but does not explicitly state when to use this tool versus alternatives like create_diagram or modify_diagram. It implies usage for conversion tasks but lacks explicit guidance on when not to use it.

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

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

With no annotations provided, the description takes on the burden of behavioral disclosure. It explains that patches are deep-merged, lists are replaced wholesale, and typed diagrams are re-rendered from a spec. It does not explicitly mention side effects like file overwriting or irreversibility, but the modification behavior is substantially disclosed.

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: purpose first, critical prerequisite second, then the typed-diagram special case with a concrete example. It earns its length, though the phrase 'The node/connection operations below' is slightly awkward because those operations are in the schema, not literally below in the description.

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

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

Given the tool's complexity and the existence of an output schema, the description covers most needed context: preconditions, diagram-type branching, and patch semantics. However, the update_spec/schema mismatch and the lack of explicit note about whether the file is saved in place leave a small but meaningful gap.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaningful semantics around update_spec patches and list replacement, but there is a notable inconsistency: the input schema's operations description lists only add_node, remove_node, update_node, add_connection, and remove_connection, while the description introduces update_spec as a valid operation. This creates ambiguity for an agent mapping the description to the schema.

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

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

The description clearly states a specific verb and resource: 'Modify an existing Excalidraw diagram created by this tool.' It distinguishes itself from create_diagram by emphasizing iterative editing of existing diagrams without recreation, and it lists concrete supported actions like adding components, removing nodes, updating labels, and rewiring connections.

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 guidance: call get_diagram_info first before modifying, and it clearly separates typed diagrams (use update_spec patch) from architecture/flowchart diagrams (use node/connection operations). This tells the agent exactly when and how to use the tool relative to the diagram type.

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

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

No annotations provided, so the description must cover behavioral traits. It describes what is reported (dependents, blast radius, dependencies) but does not explicitly state that it is read-only or safe. The nature of 'impact analysis' suggests no side effects, but it's not explicit.

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

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

The description is two sentences, front-loading the purpose and listing what is reported. No redundant information.

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

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

Given the presence of an output schema, return values need not be explained. However, the description does not detail the output structure or provide examples. The overall context is adequate for understanding the tool's function.

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

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

The description explains the 'service_id' parameter through context ('if service_id fails'), but the 'graph_path' parameter (with default) is not mentioned or explained. With 0% schema description coverage, the description should have covered both parameters.

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

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

The description clearly states the tool's purpose: impact analysis for service failure, listing direct dependents, transitive blast radius, and dependencies. This distinguishes it from sibling tools like kg_path or kg_render.

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

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

The description implies usage for failure impact analysis, but does not explicitly state when not to use or provide alternatives. However, the context is clear enough for an AI to decide.

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