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

Without annotations, the description should disclose behavioral traits. It states capabilities but does not mention side effects, authentication, rate limits, or whether the tool is read-only (it is not, as it creates chat history). Basic transparency but insufficient depth.

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

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

A single sentence listing key features. It is concise and includes the main action. However, it could be front-loaded with a clearer verb (e.g., 'Send a chat message to a model') and structured with bullet points for readability.

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 (5 params, 2 required) and no output schema, the description mentions supported features but does not detail response format or how to interpret results. It provides enough context for basic use but lacks completeness for advanced scenarios.

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 80% (high), so the description does not need to add much. It mentions features that map to parameters (e.g., 'system messages' relates to role enum) but does not explain parameter details beyond the schema. Baseline score 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 chats with a model using conversation messages, and lists supported features (system messages, multi-turn, tool calling, options). This differentiates it from sibling tools like ollama_generate, which is likely for single-turn generation.

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 mentions features but does not provide explicit guidance on when to use this tool vs siblings like ollama_generate. It implies usage for conversational scenarios but lacks exclusion criteria or alternative recommendations.

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

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

No annotations are provided, so the description must disclose behavioral traits. It only states the action without explaining side effects (e.g., disk usage, permissions required, whether the original is affected) or any constraints.

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?

Very concise at one sentence, front-loading the action. However, it could include a brief note on output or usage without becoming verbose.

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

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

No output schema exists, so the description should explain return values (e.g., success confirmation). It also lacks behavioral details to help an agent decide between sibling tools, given the simple task.

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 67% (source and destination have basic descriptions, format lacks description). The tool description adds no additional meaning beyond the schema, and the format parameter is not explained despite having enum options.

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 action: 'Copy a model' and specifies the resource (model) and result ('duplicate with new name'). This distinguishes it from siblings like ollama_create or ollama_delete.

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 like ollama_create or ollama_pull. The description does not mention scenarios, prerequisites, 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?

No annotations; description does not disclose side effects (e.g., overwrites existing model, requires pulling base model, or modifies local storage).

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, no redundancy, efficient. Could add a bit more context 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?

No output schema, no annotations; description omits important context like conflict behavior, required permissions, or outcome (e.g., local file creation). Incomplete for a tool with 6 parameters.

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 83%; description adds 'structured parameters' but not much beyond what schema already provides. Baseline 3 applicable.

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 'Create a new model with structured parameters' and distinguishes from sibling tools like ollama_copy, ollama_delete, etc.

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?

Implies usage for creating a new model, but no explicit guidance on when to use vs alternatives or prerequisites (e.g., base model must exist).

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 full burden. It states the destructive action and disk space effect, which is adequate but lacks details like irreversibility or any 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 concise sentences with no fluff. Every word adds 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?

Given the low complexity (2 params, no output schema), the description is fairly complete but could mention that deletion is permanent or explain the format parameter's purpose.

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 50% (only 'model' has a description). The description does not add meaning for the 'format' parameter (enum with defaults) 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 clearly states the action ('Delete a model from local storage') and the effect ('removes the model and frees up disk space'). This distinguishes it from siblings like ollama_chat or ollama_list.

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 (e.g., when to delete vs push/pull). No prerequisites or warnings about the model being in 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 should disclose behaviors. It states the output type but lacks details on side effects (none expected), permissions, or rate limits. Adequate for a simple read-like operation.

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, concise and front-loaded with purpose. Every word is necessary.

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?

No output schema; description could mention vector dimensions, normalization, or use cases. Lacks detail on return format but is minimally sufficient.

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 67%, description adds no extra meaning beyond what schema already provides for model and input. Format parameter has enum and default in schema. Baseline 3 since description is not incorrect but adds minimal value.

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

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

Description clearly states the action (generate), resource (embeddings), and output (numerical vector representations). It distinguishes from siblings like ollama_chat and ollama_generate which produce text.

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 embeddings vs other tools like chat or generation. No mention of use cases such as semantic search 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. Only states 'generate completion' without disclosing behavioral traits like whether it is read-only, destructive, or any side effects. Lacks information on synchronous vs streaming 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?

Two short, front-loaded sentences with no superfluous information. Every word adds 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?

No output schema and no description of return values. Lacks behavioral context that would help agent understand outcomes. For a single-turn generation tool, details like response format or streaming are missing.

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 75% (context signal), but description adds no additional meaning beyond what input schema already provides. Does not elaborate on parameters or how 'options' or 'format' affect generation.

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 'generate' and resource 'completion from a prompt'. Distinguishes from sibling 'ollama_chat' by noting it's simpler and for single-turn completions.

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 mentions when to use this tool: for single-turn completions. Contrasts with 'chat' (sibling ollama_chat) which implies multi-turn, providing clear guidance on 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?

No annotations are provided, so the description must fully disclose behavior. It states the return fields (names, sizes, dates) but lacks detail on read-only nature, authentication needs, or edge cases like empty results. For a simple listing tool, this is adequate 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?

The description is a single, front-loaded sentence that conveys all essential information. No unnecessary words, making it highly efficient for an AI agent to parse.

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 low complexity, one optional parameter, and no output schema required, the description fully covers what the agent needs: the action, the result contents, and the optional format. No gaps are evident.

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 one parameter ('format') with complete description in the schema itself (enum and default). The tool description adds no extra semantic value beyond what the schema already provides, 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 action ('List'), the resource ('all available Ollama models installed locally'), and the returned information ('model names, sizes, and modification dates'). It effectively distinguishes from sibling tools like ollama_show or ollama_ps by focusing on listing local models.

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

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

The description implies the usage context (listing installed models) but does not provide explicit guidance on when to use this tool versus alternatives like ollama_show for details or ollama_ps for running models. No exclusions or prerequisites are 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?

Description accurately states behavior but does not disclose additional traits like authorization or side effects. Since no annotations, agent must infer safety.

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, front-loaded with key action and resource, no extraneous 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?

Adequate for a simple list tool with one optional parameter and no output schema. Could mention that the output is in JSON or markdown as per the format 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 description coverage is 0% and the tool description does not mention the format parameter or its allowed values (json, markdown). Thus adds no 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?

Clearly states the tool lists running models currently in memory. Distinguishes from sibling ollama_list which likely lists all models.

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 ollama_list or ollama_show.

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 full burden for behavioral disclosure. It states the tool downloads a model, implying network usage and local storage. However, it does not mention whether it overwrites existing models, handles authentication, or any rate limits. The description is basic but not misleading.

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: two sentences that directly convey the action and effect. Every word serves a purpose, and the primary verb appears first. There is no unnecessary elaboration.

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

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

Given the simplicity of the tool (pull a model), the description covers the main intent. However, it lacks details on return format, progress indication, error handling, or prerequisites (e.g., Ollama server running). With no output schema, the agent may not know what to expect from the call.

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 moderate description coverage (67% per context signals). The description does not add any parameter-level information beyond the schema. Since schema descriptions are fairly clear for 'model' and 'insecure', and 'format' has an enum, the lack of extra context in the tool description is acceptable but not improved.

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: pulling a model from the Ollama registry and making it available locally. The verb 'pull' matches the tool name, and the resource 'model' is explicit. However, it does not explicitly distinguish from siblings like 'ollama_push' or 'ollama_copy', though the action is sufficiently 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 provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or compare to sibling tools such as 'ollama_create' or 'ollama_download' (if existed). The agent is left to infer usage context.

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

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

No annotations provided, so description must fully disclose behavior. Describes upload action but omits details about overwrite behavior, authentication, rate limits, or the effect of the 'insecure' parameter. Significant gaps.

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

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

Two concise sentences with no redundant information. Could be slightly improved by front-loading key info, but overall 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 3 parameters, no output schema, and no annotations, the description is insufficient. Missing error cases, return format, prerequisites, and detailed usage steps.

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 67% (2 of 3 params described). Description adds no extra meaning beyond the schema—repeats 'push' and 'local to remote' but doesn't explain model naming, insecure usage, or format output.

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 ('push') and resource ('model to the Ollama registry'), clearly indicating the action. It distinguishes from sibling tools like ollama_pull (download) and ollama_list.

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?

Implies usage: uploading a local model for remote availability. However, lacks explicit when-to-use vs alternatives, prerequisite (model must exist locally), or context about when to choose this over ollama_copy.

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. The verb 'show' strongly implies a read-only operation with no side effects, and the listed details indicate the scope. However, it does not explicitly confirm non-destructiveness or mention any required permissions or rate limits.

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, clear 15-word sentence. It front-loads the action and resource, and every word contributes meaning. No unnecessary details.

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

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

For a simple information-retrieval tool with two parameters and no output schema, the description covers the essential purpose and scope. It could specify that the output format is configurable and mention the response style, but the format parameter and sibling context make it adequate.

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 extra meaning beyond the schema for the two parameters ('model' and 'format'). It mentions 'modelfile, parameters, and architecture' but does not tie these to parameters.

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

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

The description clearly states the action ('Show detailed information') and the resource ('specific model'), and lists included details (modelfile, parameters, architecture). This distinguishes it from sibling tools like ollama_list (lists models) or ollama_chat (conversation).

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 retrieving model details, but does not explicitly state when to use this tool over alternatives (e.g., ollama_list for brief info, ollama_pull for downloading). No when-not or sibling comparisons are 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?

With no annotations, the description covers basic behavioral traits: it fetches a web page, returns specific fields, and requires an API key. However, it omits details like rate limits, error handling, or authentication specifics beyond the key.

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 purpose. Every sentence adds value; no 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?

Given only 2 parameters and no output schema, the description covers the basic return fields but lacks details on output structure variations per format, pagination, or size limits.

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 50% (only 'url' has a description). The description adds no extra meaning beyond the schema, such as explaining when to use json vs markdown for the 'format' 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 action ('fetch'), the resource ('web page by URL'), and the return values ('page title, content, and links'). This distinguishes it from sibling tools like ollama_web_search.

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

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

It mentions the prerequisite 'Requires OLLAMA_API_KEY environment variable' but does not specify when to use this tool versus alternatives (e.g., ollama_web_search) or provide exclusions.

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

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

With no annotations, the description carries the full burden. It discloses that the tool accesses an external API and requires a key, but does not discuss potential side effects, rate limits, or data persistence. For a read-only search tool, this is adequate but not comprehensive.

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

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

The description is two sentences, front-loaded with the primary action, and includes a key requirement. No unnecessary words or repetition.

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

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

The description lacks information about the output format (e.g., what fields are returned in JSON or markdown). Without an output schema, the agent may not know how to parse results. For a tool with a simple interface, it is marginally complete.

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

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

The input schema already describes all three parameters (query, max_results, format) with high coverage. The description adds no new semantic detail beyond the schema, earning a baseline score of 3.

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: performing a web search using Ollama's API. It explicitly distinguishes from sibling tools like ollama_chat and ollama_web_fetch by specifying it searches the web, not chat or single-page fetch.

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

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

It mentions the prerequisite (OLLAMA_API_KEY) and the benefit (reducing hallucinations), implying use when current information is needed. However, it doesn't explicitly state when not to use it or provide direct comparisons to alternatives like ollama_web_fetch.

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