KumoRFM MCP Server

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

The description discloses key behaviors: sets environment variable, initiates OAuth2 flow if needed, and takes direct API key. Annotations are neutral, so description adds value.

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 at four sentences, front-loaded with purpose, and efficiently covers the process without extraneous detail.

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

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

Given the tool's simplicity and presence of an output schema, the description provides adequate behavioral and usage context. It could mention output details if schema is insufficient.

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

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

With 0% schema coverage, the description compensates partially by explaining the api_key parameter's role. However, it omits any mention of api_url, leaving its purpose unclear.

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

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

The description explicitly states the tool authenticates a KumoRFM session, which is distinct from sibling tools like evaluate or predict. It uses a specific verb and resource.

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 specifies when to use: needed once before predicting or evaluating. It explains two authentication modes (API key or OAuth2) but does not explicitly list circumstances where it should not be used.

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

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

Annotations already indicate read-only, non-destructive, idempotent behavior. The description adds valuable context about prerequisites (graph materialization, authentication) and a tip to consider label distribution, further guiding agent behavior without contradictions.

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 efficiently structured in 4 sentences with the main purpose upfront. It is concise but could be slightly tighter; the 'Important' line is relevant but somewhat separate.

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 (6 parameters, output schema exists), the description covers prerequisites and a usage tip. Return values are not detailed but output schema exists, so this is acceptable. Minor gaps in describing output format are compensated by 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?

Input schema has 100% parameter description coverage, so description adds no extra parameter details beyond the schema. Baseline score of 3 is appropriate as the schema already 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 evaluates a predictive query and returns performance metrics comparing predictions to ground truth. It distinguishes from sibling tools like 'predict' and 'explain' by focusing on post-hoc evaluation.

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 important prerequisites (materialized graph, authenticated session) and advises reading documentation. It does not explicitly exclude alternatives or specify when not to use, but context is clear for evaluation tasks.

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

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

Annotations already indicate readOnlyHint=true and idempotentHint=true. The description adds value by disclosing that the returned prediction may differ from `predict` due to floating-point precision, and that the run mode is fixed. This provides context beyond what annotations offer.

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 moderately sized but includes repetitive directives (two 'Important:' notes) that could be merged. It is front-loaded with the main purpose, but could be streamlined for better 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 and the presence of an output schema, the description effectively covers prerequisites, limitations (single entity, fixed run_mode, precision differences), and provides documentation links. It fairly well equips the AI 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 minimal extra parameter information (e.g., fixed run_mode) but mostly reiterates constraints already documented in the schema. No significant additional semantic 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?

The description explicitly states the tool's action: 'Execute a predictive query and explain the model prediction.' It clearly distinguishes from the sibling `predict` tool by noting that the explanation may differ due to floating-point precision and that only a single entity can be explained at a time.

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 preconditions: graph must be materialized and session authenticated. It specifies that only a single entity is supported and that `run_mode` is fixed to 'fast'. It also directs users to documentation before executing or analyzing, offering clear guidance on when and how to use 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?

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds behavioral context by specifying it searches locally and cannot access remote storage, which complements the annotations.

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

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

Two concise sentences: the first states the core purpose, the second clarifies scope. No redundant words, and the information is front-loaded for quick comprehension.

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

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

Given the tool's simplicity (2 parameters, 1 required), the presence of an output schema, and the annotations, the description fully covers purpose, scope, and parameter hints without needing to explain return values or error behavior.

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 covers both parameters with descriptions. The description adds value by providing concrete file type examples (CSV, Parquet), which helps users understand what 'table-like' means, going beyond the schema's formal definitions.

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

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

The description clearly states the tool's function ('Finds all table-like files') with specific examples (CSV, Parquet), and distinguishes it from siblings like 'inspect_table_files' by focusing on discovery rather than inspection.

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

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

The description explicitly limits usage to local directories and warns against using it for remote storage like S3. This provides clear when-to-use and when-not-to-use guidance, though it does not directly suggest alternative tools.

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

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

The description fully aligns with the annotations (readOnlyHint=true, destructiveHint=false). It adds context such as the tool being purely informational, the importance of reading specific docs before certain actions, and internal notes. No contradictions.

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 thorough but somewhat lengthy. It is well-structured with sections and highlighted important points, which is appropriate for a documentation tool. However, it could be slightly more concise without losing clarity.

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

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

The description covers all necessary aspects: what the tool does, when to use it, parameter details, and additional context like the internal note and prerequisite readings. With an output schema present (indicated by context signals), the lack of return value description is acceptable.

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 explicitly lists the four possible resource URIs from the enum and explains what each documentation resource covers (e.g., 'kumo://docs/overview' for overview, 'kumo://docs/graph-setup' for graph setup). With schema description coverage at 0%, the description compensates fully by adding meaning to the parameter.

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: 'Get documentation on how to use KumoRFM.' It uses a specific verb ('Get') and resource ('documentation'), and distinguishes itself from sibling tools, none of which are documentation-focused.

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 on when to use this tool, including 'Important: Before creating and updating graphs, read the documentation first at ...', 'Before executing or suggesting any predictive queries, read ...', and 'Before analyzing the explanation output, read ...'. It also includes an internal note to avoid confusion with other meanings of RFM.

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

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

Annotations already declare readOnlyHint, destructiveHint, and idempotentHint. The description adds that the output is Mermaid markup for visualization, which is consistent but does not disclose additional behavioral traits like caching or error handling.

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

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

The description is extremely concise with two sentences. The first sentence states the core purpose, and the second adds valuable context about using the output. No unnecessary words.

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

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

The tool has a simple interface with one parameter and output schema. The description covers the output format and usage hint. However, it lacks mention of prerequisites or assumptions (e.g., that a graph must exist), which would make it fully complete.

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

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

Schema coverage is 100% and the schema description for the single parameter (show_columns) is detailed. The tool description does not add any extra meaning to the parameter beyond what is already in the schema.

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

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

The description clearly states it returns a Mermaid entity relationship diagram, which is a specific verb+resource. It distinguishes itself from siblings like materialize_graph and inspect_graph_metadata by focusing on visual representation via Mermaid markup.

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

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

The description implies usage by mentioning the returned markup can be used in an artifact, but it does not explicitly state when to use this tool versus alternatives like materialize_graph or explain. No when-not-to-use guidance 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?

Annotations already declare readOnlyHint=true, etc. The description adds context about what to verify (PKs, time columns, semantic types) but does not disclose any behavior beyond what annotations imply. No contradictions.

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

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

The description is front-loaded with the main action and provides a bullet list of items inspected. It is clear but slightly wordy (~90 words for a zero-parameter tool).

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 zero parameters, clear annotations, and presence of output schema, the description covers all necessary aspects: what the tool does, why it matters, and what it inspects.

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?

No parameters exist; schema coverage is 100%. With zero parameters, the baseline is 4, and the description does not need to compensate.

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 'Inspect the current graph metadata' and details what is inspected (primary keys, time columns, columns semantic types, links). This clearly distinguishes it from siblings like 'update_graph_metadata' or 'materialize_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?

The description implies usage before running the RFM model by stating 'Confirming that the metadata is set up correctly is crucial for the RFM model'. However, it does not explicitly say when not to use or name alternatives.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is clear. The description adds that rows are represented as dict mappings, which is useful but not critical. It does not disclose any behavioral quirks like file size limits or format restrictions.

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 sentences) and front-loaded with the core action. The second sentence details output format, which is optional but acceptable. No fluff or redundancy.

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

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

The tool has an output schema (not shown) so return format is handled. The description explains the core functionality and row representation. However, it does not specify supported file formats or error handling, which could be relevant for a 'table-like' tool.

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

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

Schema coverage is 100% with good descriptions for both parameters. The description does not add additional parameter meaning; the second sentence about row representation is about the output, not parameters. A 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 clearly states the action ('Inspect the first rows') and the resource ('table-like files'), and explains the data representation. However, it does not contrast with sibling tools like lookup_table_rows which could cause confusion about whether this tool retrieves arbitrary or only first rows.

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 inspect_table_files versus alternatives (e.g., find_table_files for searching, lookup_table_rows for specific rows). The description lacks any usage context or prerequisites.

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

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

Annotations already indicate read-only, non-destructive, idempotent. Description adds operational context: reads raw data frame, requires primary key and materialized graph. No contradictions; adds value beyond annotations.

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

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

Six sentences, each serving a purpose: main action, differentiation, anti-pattern, usage advice, prerequisites. No fluff, information is front-loaded and well organized.

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 presence of output schema and full parameter coverage, description provides all necessary contextual completeness: prerequisites, usage restrictions, differentiation, and a concrete use case. Sibling tools are referenced appropriately.

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. Description clarifies that 'ids' are primary keys and that the table must have a primary key, adding meaning beyond the schema's parameter types.

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 verb 'lookup' and resource 'rows in the raw data frame of a table for primary keys'. Distinguishes from 'inspect_table_files' by contrasting row query vs schema analysis. Purpose is specific and actionable.

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 contrasts with 'inspect_table_files', states when to use (look up detailed info about recommended items) and when not to (schema analysis). Also lists prerequisites: table must have a primary key and graph must be materialized.

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

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

Annotations already provide idempotency and non-destructiveness. The description adds important context about the dependency chain (needs re-materialization after metadata updates). However, it doesn't discuss performance or additional 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?

Two well-structured sentences with no redundant information. Purpose and dependency are clearly stated upfront.

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 parameters, an output schema exists, and annotations cover idempotency, the description provides complete guidance: prerequisite (metadata updates), purpose (enable inference), and the need for re-materialization. No 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?

No parameters are present, so schema coverage is 100%. The baseline for 0 parameters is 4, and the description adequately explains the tool's action without needing parameter-level 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?

Description clearly states the tool materializes the graph to make it available for inference operations (predict and evaluate). It distinguishes from siblings like update_graph_metadata (which updates metadata) and predict/evaluate (which use 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?

Description explains that materialization is required after graph metadata updates before inference. It implicitly tells when to use it, but doesn't explicitly state when not to use it or mention alternatives, though siblings provide context.

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

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

Annotations indicate readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=false. The description confirms the read-only, non-destructive nature by discussing predictions and output formats. It adds value by detailing output formats per task type, which is beyond what annotations provide, and does not contradict annotations.

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

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

The description is structured with a clear first sentence stating purpose, followed by prerequisites and detailed output format tables. It is somewhat long but the tables are necessary for clarity and well-organized. Front-loading the purpose and prerequisite is effective.

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 (6 parameters, 2 required, multiple task types) and the existence of an output schema, the description provides complete context: prerequisites, output formats for all task types, and a pointer to further documentation. It sets clear expectations for the user without relying solely on structured fields.

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 6 parameters thoroughly. The tool description does not add additional meaning beyond what the schema provides; it only mentions prerequisites and output formats. Baseline 3 is appropriate when schema covers all parameters.

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

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

The description clearly states 'Execute a predictive query and return model predictions', specifying the verb 'execute' and the resource 'predictive query' and 'model predictions'. It distinguishes from sibling tools like 'explain' or 'evaluate' by detailing output formats for different task types (binary classification, multi-class, regression, temporal link prediction), making the tool's purpose unmistakable.

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

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

The description explicitly states prerequisites: 'The graph needs to be materialized and the session needs to be authenticated before the KumoRFM model can start generating predictions.' It also instructs users to 'read the documentation first at kumo://docs/predictive-query' before use. While it doesn't explicitly list when not to use this tool or alternatives, the prerequisites and doc reference provide clear context.

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

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

Annotations provide idempotentHint=true, and the description's 'partial update' and 'omitted fields untouched' align with this. However, the description adds little beyond annotations—no mention of destructive potential or rate limits. Since annotations cover idempotency, a 3 is appropriate.

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

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

The description is structured with bullet points and sections, front-loading the core action. It is somewhat lengthy but each sentence adds information. Could be trimmed slightly without loss, but overall well-organized.

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 (nested objects, multiple operations), the description covers all aspects: adding/updating/removing tables and links, semantic types, and references to documentation. Output schema exists, so return values need not be detailed. The description is thorough and leaves no major gaps.

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

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

Schema coverage is 100%, but the description adds value by explaining the significance of metadata (RFM model), the role of semantic types, and procedural advice (batch operations, follow-up steps). It supplements the schema's detailed property descriptions with contextual meaning.

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

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

The description clearly states the tool's purpose: 'Partially update the current graph metadata.' It lists key operations like updating primary keys, time columns, semantic types, and links. However, it does not explicitly distinguish from sibling tools like inspect_graph_metadata or materialize_graph, though the action is inherently different.

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 includes guidance: metadata is crucial for RFM model, advises double-checking semantic types, ensuring tables are linked, and references documentation. But it lacks explicit instructions on when not to use this tool or what alternatives exist (e.g., using inspect first). The advice is useful but not comprehensive.

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