bots

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

With no annotations, the description must carry behavioral transparency. It reveals the reply includes emotion metadata, mentions session management, and indicates rate limits via free preview limits. However, it does not describe error handling, authentication details, or response structure beyond emotion metadata.

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 concise paragraph with no unnecessary words. Front-loaded with the main action, each sentence adds relevant information (emotion metadata, free preview, session handling, examples).

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 lack of output schema, the description covers essential aspects: functionality, authentication, session continuity, and examples. It could mention error cases (invalid slug) or rate limit specifics, but overall provides sufficient context for correct usage.

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 value by explaining session_id purpose (continuation) and providing example slugs. While schema already does most work, the description enhances context.

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 sends a message to a bot and receives a reply with emotion metadata. It distinguishes itself from sibling tools (get_bot, get_skill, list_bots, search_bots) which are about bot information retrieval, not 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 explains when to use: for conversational interaction with a live bot. It covers free preview limits and how to bypass them (purchased bots or API key), and mentions session_id for continuation. However, it lacks explicit exclusions or comparisons to alternatives, though siblings have clearly different purposes.

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 of behavioral disclosure. It lists what the tool returns (name, tagline, pitch, etc.) and implies a read-only operation, but does not mention authentication, rate limits, or error conditions. For a simple GET-like tool, this is adequate but not exemplary.

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, well-structured sentence that front-loads the purpose and includes all necessary information without any 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?

For a simple tool with one parameter and no output schema, the description fully explains the input (slug source) and output (card fields). The return values are enumerated, making it complete for the agent.

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

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

Schema coverage is 100% with the slug parameter well described. The description adds value by explaining that slugs can be found via list_bots or search_bots, providing extra context beyond the schema.

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

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

The description clearly states the verb 'Get' and the resource 'full card for one URBot bot by slug', listing specific fields included. It distinguishes from siblings like list_bots and search_bots by focusing on a single bot identified by slug.

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 tells when to use (when you need full details of a specific bot) and how to obtain slugs (via list_bots or search_bots). It does not explicitly mention when not to use, but the guidance is clear and adequate.

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 discloses key behavioral traits: uses live endpoint when credentials available, otherwise falls back to bundled catalog snapshot (marked in frontmatter). This is transparent about data source and fallback. Does not mention side effects, rate limits, or auth beyond 'credentials available', which is understandable for an export 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?

Three sentences, front-loaded with the core action. Contains technical details but no fluff. Could be slightly more concise, but acceptable for the complexity.

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

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

For a tool with 1 simple parameter, no output schema, and no annotations, the description covers output format, use case, and fallback behavior. It doesn't specify exactly how the file is returned (e.g., download link vs inline), but the mention of dropping it into agents implies a file artifact. Reasonably 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% with a clear parameter description ('Bot slug, e.g. "chef"'). The description adds context that the slug identifies a URBot bot, but this is implicit from the tool name. Baseline 3 applies as the schema already does the job; the description adds minimal additional value.

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

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

The description clearly states the tool generates a SKILL.md file for a bot, specifying the output format (YAML frontmatter + system prompt + capability profile) and its purpose (agent-compatible skill). It distinguishes from siblings like chat_with_bot, get_bot, list_bots, and search_bots by focusing on export for skill integration.

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 context on when to use: to convert a bot into a native skill for compatible agents. Mentions fallback behavior (live endpoint vs bundled catalog) based on credentials, giving implicit guidance on prerequisites. Lacks explicit when-not-to-use or alternative comparisons, but the sibling context and description imply the 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 takes on full burden. It discloses that the tool lists bots with pricing tiers and includes a privacy statement about data ownership and local execution. This provides behavioral context beyond the schema.

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

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

The description is three sentences. First sentence states the main purpose and returned fields. Second explains optional filter and usage. Third adds a privacy note. Every sentence adds value; no waste.

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 is a simple list with one optional parameter and no output schema, the description covers the main aspects: what is returned, filtering, how to use results, and data ownership. It could mention pagination or result limits, but overall is 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% (single optional parameter with description). The tool description adds many example categories beyond what the schema provides, which helps the agent understand valid inputs.

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 the verb 'List' with the resource 'URBot catalog' and specifies the fields returned (slug, name, tagline, category, price tiers). It clearly distinguishes from sibling tools like chat_with_bot and get_bot by stating the resulting slug can be used with those tools.

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

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

The description explains when to use this tool (to browse/filter the catalog) and how to use the results (with get_bot, chat_with_bot, or get_skill). It does not explicitly exclude other tools like search_bots, but the usage context 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, but the description discloses what is returned (top matches with specific fields) and implicitly indicates a read-only search operation. No side effects or 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?

Two sentences: first explains functionality, second gives usage guidance. No wasted words, front-loaded with key 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?

For a simple search tool with one parameter and no output schema, the description covers purpose, usage, and behavior adequately. Could include pagination details, but not critical.

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 one parameter (query) described as 'Free-text keywords'. The description adds usage examples but doesn't provide additional semantic depth 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 tool performs keyword search across multiple fields (names, taglines, categories, knowledge topics, capability pitches) and returns specific fields (slug, name, category, price, matching reason). This distinguishes it from siblings like list_bots and get_bot.

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 says to use this when you know the task but not the specific bot, and provides concrete examples. It doesn't mention when not to use, but the context is clear.

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