Hydra ACI

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

No annotations are provided, and the description does not disclose behavioral traits such as side effects, authentication needs, error handling, or whether the call is destructive. The agent gets no context beyond the basic 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?

The description is a single, concise sentence with no wasted words. However, it could benefit from structuring to highlight parameters or usage scenarios more clearly.

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 (calling a mounted capability), the description is minimal. No output schema exists, and it doesn't explain return values, error conditions, or typical use cases. Schema coverage is high, but completeness suffers from lack of behavioral details.

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 description adds value by clarifying that tool_name can be a canonical id, namespaced name, or original tool name—expanding on the schema's 'Capability id/name or original Hydra tool name'. The arguments parameter remains generic but is adequately described.

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 (call), the resource (mounted Hydra capability), and three identification methods (canonical id, namespaced name, original tool name). This specificity distinguishes it from siblings like hydra_mount or hydra_execute.

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 how to identify the capability but provides no guidance on when to use this tool versus alternatives like hydra_execute or hydra_probe. No explicit when-not-to-use or comparison with siblings.

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 carries full burden for behavioral disclosure. It only mentions 'autonomous execution' and 'complete the task', but omits critical details like whether the tool is read-only, side effects, failure behavior, or any state mutations. This is insufficient for an agent to infer safe usage.

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, highly concise with no fluff. However, it sacrifices necessary detail for brevity. It earns a 4 because every word serves a purpose, but could be expanded 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?

For a simple tool with 2 parameters and no output schema, the description is minimally viable. It covers the basic what and how, but lacks information on return values, error handling, or limitations. It meets the minimum threshold for an agent to attempt 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?

Schema description coverage is 100%, so baseline is 3. The description adds minimal semantic value beyond the schema—it restates 'target URL' and 'goal' without explaining how these are used or expected formats. No additional constraints or examples are provided.

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 does 'one-shot autonomous execution' with a target URL and goal, distinguishing it from sibling tools like 'navigate' (just navigation) and 'hydra_probe' (probing). The verb 'execute' combined with 'automatically' and the required params make the purpose unambiguous.

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., hydra_probe for exploration, navigate for simple navigation). The description lacks any 'when to use' or 'when not to use' context, leaving the agent to infer usage from the name alone.

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 only says 'inspect,' implying a read-only operation but does not explicitly state safety, side effects, or any constraints beyond the name.

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, no wasted words. Immediately communicates purpose.

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

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

Adequately describes purpose for a parameterless tool, but lacks mention of return value or any behavioral details. Could be more complete given missing annotations and 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?

Input schema is empty with 100% coverage; the description adds context by specifying what is inspected ('session and route plan'), which is valuable 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?

Description uses 'inspect' as a specific verb and clearly states the resource: 'current mounted Hydra session and route plan.' This distinguishes it from sibling tools like hydra_mount or hydra_probe.

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., hydra_probe or navigate). No when-not or exclusion criteria 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 present, so the description must disclose behavioral traits. It does not explain side effects (e.g., 'forget' may be destructive whether it requires authentication, or what happens to the data). The description is too terse to provide adequate transparency.

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

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

The description is a single concise sentence that front-loads the primary purpose. It is efficient but could benefit from slight elaboration on the action enum options.

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?

There is no output schema and the description does not mention return values or effects of each action (stats, export, forget). The agent lacks context on what to expect, especially for a tool that can be destructive (forget). The description is incomplete for safe and effective use.

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

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

Schema coverage is 100%, so the parameters are fully described in the input schema. The description adds 'for a domain' which is already implied by the domain parameter. It does not provide additional meaning beyond the schema, meeting the baseline.

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 or manage H8 web memory for a domain,' which clarifies the tool deals with memory operations. However, 'inspect or manage' is broad and could be more specific (e.g., 'Get stats, export, or forget'). It distinguishes from sibling tools like hydra_call_tool or hydra_probe but lacks explicit clarity on the exact 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?

No guidance is provided on when to use this tool versus alternatives like hydra_probe or hydra_inspect_session. There is no mention of prerequisites, when not to use it, or common use cases.

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 carries full burden. It indicates persistence and return of a catalog, but does not disclose side effects, authentication needs, or rate limits. Some behavior is implied but not detailed.

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, concise sentence that conveys the essential action and outcome without unnecessary words or structure.

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 3 parameters (1 required) and no output schema, the description covers the main goal and return value. However, it lacks details on failure modes, lifecycle management of 'persistent' workspaces, or how to unmount.

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 each parameter described. The description adds minimal additional meaning beyond the schema's definitions, such as the overall purpose of mounting and returning a catalog.

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 'mount', the resource 'website', and the outcome 'return its canonical capability catalog'. It differentiates from sibling tools like hydra_call or hydra_execute by focusing on mounting a persistent workspace.

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 (e.g., hydra_probe, navigate). It does not mention prerequisites, exclusions, 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 are present, so the description carries the full burden. It discloses that the tool does not execute generated capabilities and returns separate capability structures, but it omits safety details like whether it modifies state or requires specific permissions.

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, lengthy sentence (46 words) that tries to convey multiple concepts. It lacks breaks and prioritization, making it harder to parse quickly. A more structured format would improve scannability.

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 (nested objects, no output schema), the description fails to explain the return format or what 'browser-action fallbacks' and 'generated capability' mean. The agent would lack key contextual information 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 coverage is 100% and each parameter has a description in the schema. The tool description does not add additional meaning beyond what is already in the schema for 'goal', 'target', and 'credentials'.

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 action ('Mount a website for browser-as-probe discovery') and distinguishes the tool by mentioning returning capabilities separately from fallbacks. However, the phrasing is convoluted and may confuse agents due to dense terminology ('browser-action fallbacks', 'generated capability').

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 use for probing without executing, but it does not explicitly state when to use this tool versus siblings like 'hydra_execute' or 'hydra_mount'. No exclusions or alternative suggestions 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, description carries full burden. It says 're-scout' and 'refresh', but does not disclose potential side effects (e.g., network calls, cache invalidation, destructiveness). Insufficient for agent to understand safety implications.

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 action, no wasted words. Perfectly concise.

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 parameters, no output schema, no annotations. Simple tool, but description lacks behavioral context (e.g., is it safe to call repeatedly, side effects). Adequate but incomplete.

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, so schema coverage is 100% trivially. Baseline for 0 params is 4. Description does not add parameter info, but none needed.

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 verb 're-scout' and 'refresh' and the resource 'mounted site' and 'capability catalog'. It distinguishes from siblings like hydra_mount (attach) and hydra_probe (check).

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 when/when-not or alternatives provided. Usage is implied from the description (refresh after mount), but no guidance on when not to use or comparison to hydra_probe.

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 bears full responsibility. It mentions 'stealth browser' and 'discover session-specific actions', which hint at behaviors but lack detail on side effects, permissions, or state changes. This is insufficient for a mutation 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?

Single sentence with front-loaded verb 'Navigate'. No wasted words, but the secondary action ('discover session-specific actions') could be separated for clarity. Still highly concise.

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 one-parameter tool with no output schema, the description covers the primary action but omits what the agent receives back (return value). It mentions 'discover actions' but doesn't specify the response format. Adequate but incomplete.

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% (one parameter 'target'). The description simply repeats the schema's 'URL to navigate to' without adding new constraints or format details. With full coverage, 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 navigates to a URL and discovers page actions. It uses a specific verb ('navigate') and resource ('stealth browser'), distinguishing it from sibling tools like hydra_execute or hydra_probe.

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 navigation tasks but provides no explicit guidance on when to use vs alternatives, no prerequisites, and no when-not-to-use information. The intent is clear from the name but undeveloped.

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