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

No annotations are provided, so the description carries the full burden. It does not disclose whether the tool reads or writes, whether it requires an active daemon, what happens if port is omitted, 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?

The description is a single short sentence, but it is not well-structured; the phrase 'capture status and session selector' is ambiguous and front-loads unclear 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?

Given the presence of an output schema, return values need not be explained, but the description still fails to clarify the tool's purpose, when to use it, or the parameter's semantics. The description is too thin for a tool with a unique role in a set of nine siblings.

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 only says the port selects a daemon but does not explain the expected format (e.g., number vs string), default behavior, or what happens if the parameter is omitted. This is insufficient for a parameter that is entirely undocumented elsewhere.

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 'Capture status and session selector' is confusing and tautological. It is unclear whether the tool retrieves capture status, selects a session, or both; 'session selector' is not a recognizable verb+resource. It does not distinguish itself from siblings like list_capture_sessions or summarize_session.

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 hint is 'use port to select one of several daemons,' which is a parameter usage note, not guidance on when to use this tool versus alternatives. No condition, prerequisite, or sibling tool is 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?

No annotations are provided, so the description carries the burden. It usefully discloses the categories of information returned (operations, discovery filters, limits, write policy), which tells an agent this is a safe self-description rather than a mutation. However, it says nothing about permissions, whether the policy is dynamic, or freshness of the described policy.

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 that enumerates exactly what is returned with no filler. Every clause earns its place.

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 the description need not explain return values. Combined with zero parameters and a clear enumeration of the described domains, the definition is essentially complete for a simple introspection tool; only explicit usage guidance 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?

The tool takes zero parameters, so the schema-baseline is 4. The description adds no parameter detail, but none is needed since there is nothing to parameterize.

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 specific verb ('Describe') and enumerates the resource scope: hwlog operations, discovery filters, limits, and the current MCP write policy. This clearly separates it from the data-oriented siblings like query_logs or list_boots, which fetch logs rather than describe system capabilities. It stops short of naming siblings, but the distinction is self-evident.

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 only implied: the mention of 'current MCP write policy' hints that an agent should consult this before attempting writes, but there is no explicit when-to-use statement, no prerequisite guidance, and no stated alternative. An agent can infer it is a discovery/introspection call, but nothing in the text confirms 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 provided, so the description carries the full burden. It does disclose output variability ('when available') and that the artifact includes both raw and decoded forms, but says nothing about behavior when no crash exists, permissions, or whether the call is read-only. Useful but incomplete for a zero-annotation 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 short sentences, front-loaded with the payload description and followed by the default behavior. The closing remark about decoded frames is mildly editorial but functions as useful prioritization guidance rather than filler.

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-value documentation is not required, and the description correctly focuses on content shape and defaulting. For a simple two-param read tool the definition is nearly complete, with only the 'session' parameter and empty-result behavior 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 description coverage is 0% for two parameters, so the description must compensate. It explains the crash_id default ('most recent crash') but leaves the 'session' parameter entirely undefined, so half the parameters remain semantically opaque.

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 specific verb and resource ('get crash artifact') and immediately enumerates the payload (raw panic lines + decoded backtrace). An agent can distinguish it from query_logs or summarize_session without opening a schema, though it never names a sibling explicitly.

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?

'Defaults to the most recent crash' implies the common invocation pattern, so usage is inferable. However, there is no explicit when-to-use guidance versus siblings like query_logs or list_boots, and no stated prerequisite (e.g. an active crash session).

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. It discloses the per-boot breakdown and a useful interpretation heuristic (many short boots = rebooting device), but says nothing about read-only safety, whether the session parameter defaults to a latest/active session, or ordering. Output schema exists, so return values need limited explanation.

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, front-loaded with the resource and its contents, followed by the diagnostic hook. No redundant restatement of the name; slightly informal phrasing but every clause earns its place.

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 output schema covers return values and the description adds a diagnostic interpretation, but the undefined session parameter and its default behavior leave a real gap for an agent deciding how to call it. Adequate but incomplete for a session-scoped listing tool.

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 single 'session' parameter has 0% schema description coverage, and the description never mentions it — not what a session identifier looks like nor what happens when the optional parameter is omitted (default null). With low coverage the description should compensate but adds nothing here.

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 specific verb+resource ('Boot cycles in the session') and enumerates what each entry contains (start time, line/error/crash counts). It is distinguishable from siblings like query_logs or summarize_session, though it does not explicitly name an alternative.

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?

Gives a concrete diagnostic trigger: 'check this first when behavior looks wedged,' which tells the agent when this tool is the right entry point. It stops short of naming an alternative tool or exclusion, so it is clear context rather than full when/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?

With no annotations, the description carries the full burden, and it does disclose ordering ('oldest first') and the aggregate counts returned. However, it says nothing about pagination, volume limits, cost, or whether an empty result is possible for a session-enumeration call.

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 resource and the ordering detail. Every clause earns its place.

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 the description still volunteers the ordering and the summary fields. For a zero-parameter listing tool this is nearly complete, with only pagination/volume behavior 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter-level information is needed or missing.

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 clear verb (implicit 'list') plus the resource ('recorded sessions') and the fields surfaced (port, boot and crash counts), so the agent knows this is a broad enumeration of capture sessions. It does not explicitly distinguish itself from siblings like list_serial_ports or list_boots, but 'capture sessions' is specific enough to separate it.

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 versus alternatives such as summarize_session, capture_status, or query_logs. The parenthetical '(oldest first)' hints at the listing use case, but there is no explicit when/when-not or routing language.

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 the full burden and does reasonably well: it discloses a hard 100-port output cap, that all supplied filters are AND-combined, and the important side-effect guarantee that discovery never opens a serial port. It omits permission/auth requirements and what happens when the 100-port cap truncates results.

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 compact sentences, front-loaded with purpose and then the filter grammar. No filler, every clause carries operational meaning.

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-value explanation is not required, and the description covers filters, combination logic, the result cap, and the non-opening guarantee. The only gap is that the 100-port limit is not framed as truncation or pagination, leaving unclear how an agent retrieves ports beyond the cap.

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, and it does: it defines match as a case-insensitive substring over port/description/board hint/location, vid/pid as exact integer USB IDs, serial_number as an exact USB serial, and states that filters combine. Every one of the four otherwise-undocumented parameters is fully specified.

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 opens with a specific verb+resource ("Discover boards") that maps directly to enumerating serial ports, and the filter semantics make the scope unmistakable. It does not name or contrast any sibling tool, but the resource is distinct enough from list_boots/list_capture_sessions/describe_capabilities that confusion is unlikely.

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?

"Discover boards; filter before limiting output to 100 ports" gives implied guidance on when to reach for this tool and on filtering first, but it never names an alternative or an explicit when-not-to-use condition. There is no routing advice toward siblings like describe_capabilities or query_logs.

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 behavioral burden, and it does disclose two meaningful traits: the output is bounded at 500 lines and results are ordered newest-last. It omits the safety profile (read-only), any permission/auth requirements, and what happens when the boot index is out of range, so it is only partially transparent.

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 core purpose and the 500-line bound are front-loaded in one sentence, followed by a compact one-line-per-parameter glossary. No sentence is redundant and nothing is buried.

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-value details are rightly omitted, and the pagination/limit behavior is covered. But with 7 parameters, 0% schema coverage and no annotations, three parameters (tag, tail, session) are undefined anywhere, leaving the agent to guess at how to scope a query to a tag or session.

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, and it explains four of seven parameters with real semantics: boot's literal '-1' sentinel, level's E/W/I/D/V scale, grep's case-insensitive substring matching, and collapse_repeats' fold-into-count behavior. That is substantive meaning the schema does not carry. It leaves tag, tail and session entirely undocumented, which keeps it from a 5.

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?

Specific verb+resource ("Query captured device logs") with scope qualifier "captured" and an ordering note ("newest last"). It reads distinctly from siblings like list_boots, get_crash and list_capture_sessions. It stops short of explicitly naming which sibling to prefer for related tasks (e.g. crash retrieval), so it lands at 4 rather than 5.

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 implied by the scope (query log lines) and reinforced by the inline recommendation "boot: -1 for the latest boot cycle (recommended)", which is genuine when-to-use guidance for one parameter. However, no conditions for choosing this tool over list_boots, get_crash or summarize_session are given, and no exclusions are stated.

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 behavioral burden. It usefully discloses the environment-variable enablement gate, but says nothing about mutation semantics, whether the device replies, rate limits, targeting behavior when port is omitted, or error conditions.

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 waste. It is tight, though the second sentence is a bare operational warning rather than explanatory context.

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, but for a 3-parameter tool with zero schema coverage and no annotations the description leaves too much unresolved: port targeting, newline behavior, and the concrete consequence of the disabled state are all 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 0% for all three parameters, so the description must compensate. "Send a line" loosely hints at text/newline handling, but the optional port parameter and the default newline=true behavior are entirely undocumented in both schema and description.

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 specific verb and resource ("Send a line to a device"), which is enough to distinguish it from read-side siblings like list_serial_ports and query_logs. It does not explicitly contrast itself with the other write-ish sibling wait_for_pattern, so it falls short of a 5.

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 guidance is a gating condition ("Disabled unless HWLOG_MCP_ALLOW_SEND=1"), which describes a prerequisite rather than when to choose this tool over wait_for_pattern or other siblings. No when-to-use, when-not-to-use, or alternative routing is given.

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 and does disclose key behavioral traits: bounded scanning (at most 16 MiB), bounded output (at most 32 KiB), and the crucial caveat that counts apply only to that window. It does not cover permissions, cost, or whether results are cached, but the truncation semantics are unusually well surfaced.

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 short sentences, each earning its place, with the core capability front-loaded and the limiting/caveat facts following. No filler 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?

For a bounded-summary tool with an output schema present (so return shape needn't be explained), the description covers scope, limits, caveats, and the parameter's usage. Minor gap: it never clarifies what a 'fault' or 'coverage' entry contains, though the output schema likely covers this.

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 0% and the single 'session' parameter is undocumented in the schema, so the description must compensate. It does: 'Select a session explicitly when more than one device is in use' explains the parameter's purpose and when to supply it, though it doesn't describe the accepted identifier format.

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 specific verb+resource ('compact recorded evidence') and enumerates the content it summarizes (recent faults, counts, firmware, data coverage). It distinguishes itself from query_logs and get_crash by being a compaction/summary rather than a retrieval of individual records, though it does not name a sibling explicitly.

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?

Gives clear operative guidance: 'Check scan/storage coverage before drawing conclusions; silence is not health' and 'Select a session explicitly when more than one device is in use.' It does not name alternative tools or state when-not to use this one, so it stops short of full routing 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?

With no annotations, the description carries the full burden. It usefully discloses blocking semantics, that only NEW output is matched (a real gotcha), and a 120s timeout cap. However, it never says what happens on timeout (error, empty result, or false) or whether the call blocks the session, leaving a notable behavioral gap.

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, front-loaded with the core action and constraint ('Max timeout 120s') before the conceptual justification. Every sentence earns its place.

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 documented. Still, for a blocking primitive the absence of timeout-result behavior and any hint about the 'session' parameter leaves an agent guessing about edge cases.

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 0%, so the description must compensate. It adds real value for 'pattern' (regex) and 'timeout_s' (max 120s, beyond the schema's bare default of 30), but the 'session' parameter is entirely unexplained in both schema and description.

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 precise verb+resource+scope: blocking wait for a regex PATTERN in NEW device output. The 'NEW output' qualifier implicitly separates it from history-reading siblings like query_logs, but no sibling is named explicitly.

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?

Gives a concrete when-to-use scenario ('after flashing, assert the expected log line actually appears instead of assuming success'), which is strong context. It stops short of naming alternatives or when NOT to use it (e.g. checking already-emitted logs via query_logs).

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