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

The description does disclose the critical behavioral fact that live start/stop is always blocked, which is genuinely useful. But this directly conflicts with the annotations, which declare destructiveHint=true and readOnlyHint=false for a tool that reportedly never performs the mutating action; the agent is left unsure which signal governs, and nothing is said about what planning output is produced or whether any state changes.

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 tight sentences with the safety constraint front-loaded in emphasis, no filler. The phrasing 'Plan lifecycle URLs' is a bit cryptic, but nothing 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 needn't be spelled out, and annotations cover the safety profile (albeit inconsistently). Still, for a 2-parameter, zero-coverage schema the description should clarify the dry_run behavior and what a 'plan' result means; that gap is material for correct invocation.

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%, so the description must carry the burden. It only gestures at 'start/stop' and 'mock lifecycle', never explaining the dry_run flag, its default of true, or what happens when it is set to false (given live actions are blocked).

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 verbs 'plan' and 'simulate' against 'lifecycle', and the final sentence clarifies that live start/stop is blocked, so the agent gets a rough sense of the operation. However, it never states the resource plainly (app lifecycle) and does not distinguish this from any of the diagnostic/connection siblings, leaving the actual purpose partly inferred from the tool name.

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?

'Plan lifecycle URLs or simulate mock lifecycle' implies a planning/dry-run use case, and 'Live start/stop always blocked' tells the agent not to expect real execution. There is no explicit statement of when to prefer this over alternatives, no prerequisites, and no mention of the start-vs-stop selection logic.

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 cover safety and idempotency, but the description adds two things they do not: the operation briefly consumes a server accept slot (a real side effect on the remote side) and a successful connect is not proof of identity. Those are meaningful operational caveats beyond readOnlyHint/idempotentHint. It still says nothing about timeouts or failure modes.

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 dense clauses, no filler, with the action front-loaded ahead of the caveats. Every phrase carries information; even the terse 'no selector' is at least positioned as a qualifier rather than padding.

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 no explanation, and the 'no identity proof' note is a useful interpretation caveat. However, with zero parameters it is unexplained what host/port the probe targets (presumably configured elsewhere) and how long it waits before failing, which matters for an agent interpreting a negative result.

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 no parameter semantics to explain; baseline 4 applies. One could argue the description should explain where the connect target comes from, but that is a completeness rather than a parameter-documentation issue.

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?

It does name a concrete action (open and close a TCP connection) rather than restating the name, but 'with no selector' is unexplained jargon and the phrase 'connection_probe' is never plainly glossed as 'check that the server accepts TCP connections.' Nothing distinguishes it from siblings like rp_rx_connect or rp_connection_status, so an agent must infer the difference.

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 statement of when this tool should be chosen over rp_rx_connect, rp_connection_status, or rp_device_diagnostics. The only hint at appropriate use is the implicit 'no identity proof' caveat, which tells an agent what it cannot conclude but not when to run 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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds genuine scope information by explicitly excluding device-setting and TX-state readback, which prevents over-trusting the result, but says nothing about freshness, caching, or whether sockets are merely requested versus established.

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 sentences with zero filler, and the scope limit is placed immediately after the purpose. It is efficient, though the terseness borders on under-specification rather than optimal density.

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 presence of an output schema means return values need not be described, which compensates for part of the brevity. Still, for a status tool sitting among rp_connection_probe and three diagnostics siblings, the description does not supply enough to select it confidently or to know what question it answers.

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 and the schema-level burden is nil. Baseline 4 applies for a no-argument tool.

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?

"Report local sockets/requested RX settings" gives a verb and a resource, but "local sockets/requested RX settings" is jargon that a caller cannot easily resolve into a concrete outcome. It is not distinguishable from rp_connection_probe or rp_device_diagnostics on the strength of the description alone.

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 clause "No device setting or TX state readback" implies the tool should not be used for device-level or transmit-side information, so there is a partial when-not. However, no sibling is named as the alternative, so an agent has to guess whether rp_connection_probe, rp_device_diagnostics, or rp_system_diagnostics is the right substitute.

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 readOnly, idempotent, non-destructive, and open-world behavior. The description adds a useful negative capability ('Cannot verify running app/OS/FPGA identity') and hints at bounded scope, but lacks further behavioral context such as what the metadata includes or any rate/permission constraints. With annotations covering safety, this is adequate but not rich.

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 sentences, front-loaded with the purpose and then the key limitation. Every word earns its place with 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 zero parameters, a full output schema, and rich annotations, the description is nearly complete. It conveys the core action and a critical limitation. A brief mention of what 'app metadata' entails could push it to a 5, but for this complexity level it is 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?

The tool takes zero parameters, so the baseline is 4. The description does not need to explain any input semantics, and the schema coverage is 100%.

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 verb ('Read') and a resource ('bounded HTTP app metadata'), but 'bounded HTTP app metadata' is jargon that does not clearly differentiate this tool from siblings like rp_system_diagnostics or rp_connection_status. The negative scope statement ('Cannot verify running app/OS/FPGA identity') adds some clarity but leaves the core purpose somewhat vague.

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 (read app metadata) and gives one explicit 'when not' condition (identity verification), but it does not name alternatives or specify when to choose this tool over rp_system_diagnostics or other siblings. Guidance is only implied.

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, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds the meaningful nuance that no hardware is touched and that the target value is operator-reported rather than measured, but says nothing about freshness or scope of the reported configuration.

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 front-loaded sentence with no filler. The only shortfall is that no clause routes the agent toward or away from the sibling tools.

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 and annotations covering safety, the description needn't explain returns. However, in a cluster of five diagnostics/status siblings it leaves the agent guessing how 'profile' differs from 'diagnostics' and 'status'.

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; baseline 4 applies.

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?

States a concrete verb+resource: reports configured capabilities and the operator-reported target. The 'without hardware I/O' clause sharply separates it from the diagnostics siblings, though the vague name 'rp_profile' still leans on the description to be understood.

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 'without hardware I/O' qualifier implies when to prefer this over rp_device_diagnostics or rp_system_diagnostics, but no sibling is named and there is no explicit when-not guidance.

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?

Beyond the annotations, the description discloses important behavior: it resets RX config/FIFO, requires exclusive app ownership, closing resets tuning/rate, and there is no server ACK/readback. These are meaningful operational caveats for a destructive, non-idempotent tool, though 'RP_ALLOW_RX' could be explained more precisely.

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 text is short, front-loaded, and mostly free of waste. The fragmentary style is dense but generally earns its place by packing in lifecycle and safety caveats.

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 annotations and an output schema, the description covers the major behavioral risks: destructive reset behavior, exclusivity, live-mode gating, and lack of readback. The main gap is that frequency_hz is never addressed, but overall it is sufficient for an agent to call the tool cautiously.

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%, so the description must compensate. It helpfully enumerates valid sample_rate values, but it omits frequency_hz entirely and only indirectly gestures at acknowledge_side_effects via 'acknowledgement', leaving two of three parameters under-explained.

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 verb and resource ('Open RX') and clarifies that it resets RX config/FIFO. It is distinguishable from siblings like rp_rx_disconnect and rp_rx_read, though the phrase 'RX only' is terse and could be clearer about whether it means receive-only rather than only the RX subsystem.

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 gives prerequisites for opening RX in live mode ('RP_ALLOW_RX and acknowledgement') and notes exclusive app ownership. However, it does not explicitly say when to use this tool versus rp_connection_probe, rp_connection_status, or rp_rx_read, leaving usage largely implied.

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 destructiveHint=true, idempotentHint=false and openWorldHint=true, so the agent knows this mutates state irreversibly. The description adds genuinely useful context beyond that: the server resets RX tuning/rate and TX sockets are untouched, bounding the blast radius. It does not cover what happens if no owned socket exists or whether repeated calls error.

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 sentences, front-loaded with the action, followed by the side-effect clarification. No filler 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 zero-parameter tear-down tool with an output schema and rich annotations, the description covers the essential unknowns: what is closed, what side effect occurs server-side, and what is deliberately not touched. Only error/idempotency edge cases are left unaddressed, and idempotency is already in the annotations.

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 the schema-completeness baseline of 4 applies; there is no parameter ambiguity to resolve. The description correctly implies the target set is implicit (owned RX sockets).

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 specific verb and resource: "Close owned RX sockets," which is clearly distinct from the sibling rp_rx_connect and clarifies that only sockets this client owns are affected. It stops short of explicitly naming an alternative tool, but the action and scope are 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?

There is no explicit statement of when to call this versus alternatives such as rp_rx_connect or rp_rx_read, nor any prerequisites or conditions (e.g., must a socket be open first?). The word "owned" hints at a validity constraint but is not expanded into usable guidance.

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 annotations declare destructiveHint=true/readOnlyHint=false, and the word 'consume' explains that reason: the read drains buffered data rather than being a harmless peek. 'not calibrated RF' is genuinely useful context beyond the annotations, warning that returned values have no absolute units. It still omits that a live session is required and what happens when the buffer is empty.

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?

One compact, front-loaded sentence with no filler, and the calibration caveat is placed as a trailing qualifier where it belongs. It is efficient but telegraphic, which is part of why the guidance gaps exist.

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 structure need not be spelled out, and the annotations cover the safety profile. However, for a hardware-touching destructive read the description never states the session precondition or the drain/empty-buffer behavior, leaving a meaningful gap for the caller.

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%, so the description must carry both parameters, but neither sample_count nor preview_samples is named or explained. 'Bounded' and 'preview' only loosely gesture at them; units, defaults, and the meanings of the 1-8192 and 0-32 caps are left entirely to the schema titles.

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 gives a specific verb+resource: consume buffered float32 IQ samples and return a summary/preview. That clearly separates it from the sibling connect/disconnect/diagnostics tools. It stops short of naming a sibling or stating the buffer's source, but the action is 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?

There is no statement of when to call this versus rp_rx_connect, rp_rx_disconnect, or the diagnostics tools, and no precondition such as an active connection or a populated buffer. The agent must infer that consumption only makes sense after connecting and that repeated calls drain the stream.

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 annotations already establish readOnly, idempotent, openWorld, and non-destructive behavior, so the description correctly reinforces "no writes" without contradicting them. It adds useful context that fixed-command SSH may be used, but does not explain SSH authentication requirements, command restrictions, or execution limits beyond that phrase.

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 definition is a single front-loaded sentence with no wasted language. "Read" comes first, followed by the evidence scope and the optional SSH behavior.

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 parameterless diagnostic tool whose annotations and output schema already cover safety and return structure, the description is largely complete. It could be stronger if it clarified what "fixed-command SSH" permits, but no critical invocation detail 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?

This tool has zero parameters, so parameter semantics have no room for additional description beyond the empty schema. The baseline for a no-parameter tool is therefore 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 uses a specific verb, "Read," and names concrete evidence domains: OS, model, process, app, and FPGA. It is distinguishable from narrower siblings such as rp_device_diagnostics and rp_connection_status, though it does not explicitly contrast itself with them.

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 a read-only diagnostic collection task but never states when to use this tool instead of rp_device_diagnostics, rp_connection_probe, or other siblings. It also gives no exclusions or prerequisites for the optional SSH path.

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