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

No annotations are provided, so the description carries full behavioral burden. It hints at FastMCP sampling and a fallback condition but omits crucial traits: whether the workflow mutates state, how iterations are bounded, permission/auth requirements, cost/latency implications, and what 'sampling' means operationally.

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 short sentence with the key capability front-loaded. It is efficient, though almost too terse for a multi-step process. Given the complexity of the operation, the brevity edges into under-specification rather than pure 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?

Output schema exists, so return values need not be explained. However, for a complex multi-step, tool-using workflow with three undocumented parameters, no annotations, and no usage routing against five siblings, the description is far too thin to tell an agent how to invoke it correctly or safely.

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% for all three parameters. The description mentions no parameter behavior: it does not explain that workflow_prompt drives the sampling, that max_iterations bounds the loop, or what available_tools filters. With three undocumented params, the description fails 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?

Names a verb and resource ('Run a multi-step workflow'), which is clearer than a tautology, but 'workflow' is generic and the description gives no sense of what the workflow actually does or how it differs from sibling tool 'chat' or 'packetsniffer_ops'.

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 only conditional is 'when the client supports it,' which is about capability, not task fit. There is no guidance on when to choose this over 'chat' or 'packetsniffer_ops', and no explanation of what happens when the client does not support FastMCP sampling.

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 destructiveHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: provider auto-detection order for local runtimes, the API-key requirement for cloud providers, and per-request override semantics. It stops short of noting cost, latency, or rate-limit implications of cloud calls.

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?

Purpose is front-loaded in the first sentence, with provider mechanics second and examples last. The 'Return Format' block partially duplicates the output schema and is the one section that does not fully earn its place, but the examples themselves are compact and instructive.

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

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

With an output schema present, explaining return values is optional and the restated format is a minor redundancy rather than a gap. The description covers provider resolution, overrides, and parameter usage sufficiently; only failure modes (no provider configured, invalid API key, provider unreachable) are left unaddressed.

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

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

Schema coverage is 100%, so the baseline is 3, but the examples meaningfully add value by showing how parameters compose (system prompt alongside prompt, provider+model override together, temperature tuning). That demonstrates the override precedence described in prose but not spelled out per-parameter 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 states a specific action (send a prompt to the configured LLM) and resource, then explains the underlying mechanism: a unified client that auto-detects local providers (Ollama, LM Studio) and supports cloud providers via API keys. Sibling tools (status, help, ops, workflow) are unrelated utility endpoints, so no sibling differentiation is required for an agent to pick correctly.

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?

Usage is demonstrated through four concrete examples rather than stated explicitly; there is no 'use this when...' guidance or exclusion of alternatives. The mention of API keys for cloud providers is the only implicit prerequisite, and nothing tells the agent what happens when no provider is reachable. Adequate but with clear gaps for a tool whose behavior varies by environment.

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 behavioral burden. 'List' weakly implies a read-only operation, but there is no explicit statement about safety, side effects, authentication, or rate limits. The output schema covers return values, but behavioral traits are not disclosed beyond the verb.

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 with no filler, front-loading the action and resource. It is appropriately sized 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?

The tool is simple (zero params) and has an output schema, so return details are not needed. However, the description never explains what 'fleet surface' means or how this tool relates to sibling status and status_card tools, leaving a clear contextual gap for an agent deciding when to call it.

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

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

The tool takes zero parameters and schema coverage is 100%, so the rubric sets a baseline of 4. There are no parameters for the description to clarify, and the schema is trivially complete.

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?

State a specific verb 'List' and resource 'capabilities and fleet surface for PacketsnifferMcp', so an agent can tell it is a discovery/help tool. However, 'fleet surface' is undefined jargon and the description does not distinguish it from sibling tools like status or packetsniffer_mcp_status_card.

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 when-to-use, when-not-to-use, or alternative tool guidance is provided. The name 'help' hints at discovery, but the description itself gives no explicit context for selecting this tool over status, packetsniffer_mcp_status_card, or others.

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 destructiveHint=false, so the safety profile is covered. The description adds useful output-format context ('Prefab card') but does not describe authentication, rate limits, or other behavioral traits.

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

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

The description is a single, front-loaded sentence with no wasted words. It is slightly terse and lacks an explicit verb, but the structure is 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?

For a zero-parameter, read-only status tool with no output schema, the description provides enough context: it returns server health formatted as a Prefab card. Additional detail about card contents or call frequency could improve it, but the essentials are present.

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 tool has zero parameters, so there are no parameter semantics to explain. The baseline for a zero-parameter tool is 4, and the description does not need to compensate for any schema gaps.

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 the resource (server health) and output form (a Prefab card), which distinguishes it from the sibling 'status' tool. The verb is implicit rather than explicit, but an agent can infer it retrieves a status card.

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?

There is no guidance on when to use this tool versus alternatives such as 'status' or 'help'. The agent must infer usage from the name and description 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?

Annotations are minimal (readOnlyHint=false, destructiveHint=false), and the description carries the burden well beyond them: captures require administrator privileges, start_capture is non-blocking and survives across HTTP daemon sessions, stop_capture only takes effect on the next packet, save_path persists evidence, and dependencies (tshark, USBPcap) are flagged with live-verification caveats. This is exactly the operational context an agent needs before invoking a stateful capture 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?

For a 12-operation, 19-parameter mega-tool the length is largely justified, and the operation-by-operation bullet structure is easy to scan and front-loads the domain statement. Minor waste comes from the '[RATIONALE]' self-justification about tool limits and the somewhat redundant example block, but nothing seriously hinders 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 complexity, the description covers prerequisites, blocking semantics, background lifecycle, dependency caveats, and the return envelope ({success, operation, data}), and an output schema exists so return values need no further explanation. Nothing an agent needs to invoke these operations correctly is 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 description coverage is 100% and every parameter is documented per-operation in the schema, so the baseline is 3. The description repeats most of that (save_path use, limit bounding, direction semantics) rather than adding genuinely new per-parameter meaning, so it does not rise above 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 header names the domain (interface discovery, live capture, PCAP analysis) and each of the 12 operations is enumerated with a specific verb+resource, including the distinct USB/Bluetooth hardware-reverse-engineering group. An agent can tell exactly what any given operation does without opening the schema, and the scope is clearly distinct from siblings like workflow/help/status.

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?

Routing guidance is embedded throughout: sniff vs start_capture (blocking vs non-blocking background), decode_pcap vs analyze_pcap (deep tshark decode vs flow summary), and diff_captures 'for controlled experiments (blank label vs one dot)'. Prerequisites are also given (admin rights, tshark optional, USBPcap). What is missing is any explicit 'when not to use' or note on which operation to prefer when an agent is unsure.

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

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

No annotations are provided, so the description carries the full burden, and it does disclose the reported content (health and version). However, it says nothing about whether the call is read-only, whether it requires auth, or whether it can fail or be rate-limited. For a trivial zero-parameter endpoint the risk is low, so a middling score is fair rather than a penalty.

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?

Four words, no filler, front-loaded on the resource. It is arguably terse to the point of under-specification, but nothing in it is wasted.

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?

An output schema exists, so return values need not be explained, and with zero parameters there is little schema burden. What is missing is the usage context relative to the closely named sibling status_card and help, which leaves the definition merely adequate for a diagnostic endpoint.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool is 4. Schema coverage is 100% and the empty object schema is self-explanatory.

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 fragment 'Server health and version' names the resource and the two things it reports, but there is no verb and no differentiation from the sibling 'packetsniffer_mcp_status_card', which an agent could easily confuse with this tool. Purpose is inferable but not stated with enough precision to route confidently.

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 when-to-use guidance, no mention of prerequisites, and no reference to alternatives such as help or packetsniffer_mcp_status_card. The agent must guess the context in which this endpoint is appropriate.

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