homelab-mcp

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

With no annotations, the description carries the full behavioral burden. It does disclose one non-obvious trait beyond the schema: the path must be an 'exactly allowlisted' mount path, so arbitrary paths are rejected. However it never says where the allowlist comes from, how to discover valid entries, whether the tool is read-only, or what happens on a rejected path.

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 tight sentence with the resource stated first and the constraint second; nothing is wasted. It is perhaps too terse given the undefined allowlist, but that is a completeness issue rather than verbosity.

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 tool has only one parameter. The remaining gap is the 'exactly allowlisted' constraint: an agent cannot tell how to choose a valid path, and the schema default of '/' may not be allowlisted. That ambiguity keeps it at minimum-viable completeness.

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% for the single 'path' parameter, so the description must compensate. It clarifies that the value is a mount path (not an arbitrary filesystem path) and that it must be exactly allowlisted, which adds real meaning over the bare schema. It still gives no format examples or a way to enumerate valid values.

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 ('Report disk usage') plus a scope qualifier ('exactly allowlisted mount path'). That is far more precise than a tautology, and the sibling list (memory, service_status, uptime, etc.) covers different resources, so disambiguation is implicit. It stops short of an explicit contrast with a sibling, which is the only gap.

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 the tool is for checking disk usage on a mount, and 'exactly allowlisted' functions as a usage constraint rather than a when-to-use rule. There is no statement of when this is preferable to a sibling tool or any alternative to use instead when the path is not allowlisted.

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 exist, so the description carries the full burden. It usefully discloses that a normal error result is returned when Docker is absent, which is genuine behavioral context. However, it says nothing about the read-only nature, output verbosity, or whether it lists all vs. running containers.

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 filler. The core purpose leads and the error-behavior caveat follows efficiently.

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, and it adds the Docker-absent error behavior. It is close to complete for a no-param list tool, only missing a note on all-vs-running containers.

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 of 4 applies. The description correctly implies no input is needed to list containers.

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 (List) and resource (Docker containers) that an agent can immediately understand. It doesn't explicitly contrast with any sibling, but 'docker_containers' is distinct enough from disk_usage, memory, and service_status that differentiation is implicit.

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 service_status or health, nor any prerequisites (e.g., Docker must be running). The second sentence addresses error behavior, not usage selection.

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 behavioral burden. It discloses only that output is 'bounded' and 'raw' (unprocessed), but says nothing about read-only safety, permissions, truncation limits, or cost — thin disclosure for a tool with zero annotation coverage.

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?

It is a single front-loaded sentence with no filler, which is structurally clean. But the brevity is achieved by omission rather than efficiency — key nouns like 'fixed incident category' and 'bounded' are undefined, so terseness here borders on under-specification.

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. Yet for a tool with three undocumented parameters and no annotations, the description should supply the missing semantics (what a 'kind' is, what 'bounded' means in practice); it does not.

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% across three parameters (kind, path, service), and the description mentions none of them. The critical 'kind' parameter's allowed values or meaning are left entirely undefined, so an agent cannot know what to pass.

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 verb 'Return' and resource 'raw evidence' are identifiable, and 'bounded' plus 'fixed incident category' hint at scope. However, 'fixed incident category' is never defined (the schema's 'kind' parameter presumably encodes it), and nothing distinguishes this from siblings like incident_report or tail_logs, which plausibly return overlapping diagnostic data.

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 incident_report, tail_logs, or propose_remediation, and no prerequisites or conditions are given. 'only for a fixed incident category' hints at a restriction but never tells the agent how to know whether its situation qualifies.

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 behavioral burden. It implies a non-destructive read (a health probe returning a capability count), which is useful context, but it does not confirm read-only safety, permissions, or side effects explicitly. For a zero-parameter diagnostic this is adequate but thin.

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 identifies both outputs with zero filler. Nothing could be trimmed without losing information.

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

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

An output schema exists, so return values need not be spelled out, and the description still names the two key outputs. For a simple health probe this is nearly complete; only the when-to-use angle 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 no parameters, so the baseline of 4 applies. The description adds no parameter meaning, but none is 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?

States a specific verb (Return) and resource (server health plus configured read-only capability count), which is more informative than the sibling 'uptime' or 'service_status'. It doesn't explicitly differentiate itself from those siblings, 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?

There is no guidance on when to call this versus alternatives such as uptime, service_status, or memory, and no stated preconditions. The agent must infer that this is a broad health probe 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?

With no annotations, the description carries the full disclosure burden, and it does deliver one meaningful non-obvious trait: this tool is non-mutating ('never remediates'). However, it says nothing about what it reads, whether it writes any report artifact, permission needs, or scope of evidence collection. The safety declaration is valuable, but the behavioral picture is incomplete.

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 single clause is tight and front-loads the core idea followed by the negative constraint. It is concise to the point of under-specification, so it earns its brevity but not a high mark for 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?

An output schema exists, so return values need not be described. But with no annotations and 0% parameter coverage, the definition leaves critical gaps: what 'kind' selects, how path/service narrow the evidence, and what the tool actually produces. For a three-parameter investigation tool, this is inadequate.

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% across three parameters (kind, path, service), and the description adds no information about any of them. An agent cannot tell what 'kind' accepts, what 'path' scopes against, or how 'service' filters, so the description fails to compensate for the coverage gap.

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 frames the tool as converting read-only evidence into hypotheses, which gestures at analysis but never states plainly that it produces an incident report or what evidence it consumes. It does distinguish itself negatively from the remediation path ('this tool never remediates'), which helps separate it from propose_remediation. Still, the purpose is stated metaphorically rather than concretely.

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 when-to-use/when-not-to-use statement or naming of alternatives. The phrase 'this tool never remediates' implies the agent should reach for propose_remediation when action is needed, which is a weak but real routing signal. Usage remains largely inferred from the tool name.

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, yet it only says what is returned. It does not confirm the operation is a safe read, specify units or snapshot semantics, or note any auth requirements. The presence of an output schema covers the return shape, but the description itself adds little.

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 or redundancy. Perfectly sized for a zero-parameter read 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?

For a no-argument read tool with a defined output schema, the description is largely sufficient since return values are covered elsewhere. It could be slightly more complete by clarifying scope (e.g., system-wide vs. per-process memory) or routing against 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?

The tool takes zero parameters, so there is no parameter semantics to document. Baseline of 4 applies since the description need not compensate for anything.

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 ('Return Linux memory usage'), making the tool's function immediately clear. It does not, however, explicitly differentiate itself from siblings like disk_usage, health, or uptime, which an agent might reasonably confuse it with.

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 call this tool versus alternatives such as disk_usage or health, nor any mention of prerequisites or context. The agent must infer usage entirely from the name.

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

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

With no annotations, the description carries full behavioral burden. It does disclose one important trait: proposed commands are never executed, implying a safe, non-mutating proposal operation. However, it does not state whether the proposal is persisted, whether authentication is required, or any other side effect beyond non-execution.

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 two short, front-loaded sentences with no filler. Both sentences earn their place, though the overall terseness is a consequence of missing content rather than an efficient treatment of a well-understood 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?

Given 0% schema coverage, no annotations, and two required parameters, the description should do much more. It omits parameter meaning, usage context, and differentiation from siblings. An output schema exists, so return values need not be explained, but that alone does not compensate for the missing operational detail.

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% and both required parameters ('kind' and 'evidence_json') are completely undocumented. The description adds no meaning about valid values, expected format, or purpose for either parameter, leaving the agent unable to construct a correct call.

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 says 'Propose text-only actions,' which largely restates the name 'propose_remediation' in other words. It does not clarify what kind of remediation is proposed or distinguish this tool from siblings like incident_report or evidence_snapshot, so an agent gets little beyond the 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?

No when-to-use guidance, prerequisites, or alternatives are given. The statement 'No proposed command is ever executed here' is a safety note, not usage guidance, and it does not tell the agent when to choose this tool over the many other system/incident tools.

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 behavioral burden. It discloses a meaningful non-obvious trait, that only allowlisted services are accepted, but says nothing about failure behavior for blocked services, output format, or any rate/permission limits.

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 efficient sentence with the scope constraint front-loaded alongside the action. Nothing is wasted, though it is arguably too terse given the undocumented parameter.

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 is not expected to cover them. Still, for a tool with one required, entirely undocumented parameter, the definition leaves an agent guessing about valid input values.

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% and the single required 'service' parameter has no documentation in either the schema or description. The description does not clarify whether the value is a bare unit name, a full unit name (e.g. with .service), or how it maps to the allowlist, leaving the agent to guess.

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 (Show) and resource (systemd properties for a service), and the allowlist scope distinguishes it from broader diagnostics like health or uptime. The phrase 'selected properties' is vague about which properties are returned, but the core purpose is clear.

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 (inspect a systemd service's status) and one guardrail: only allowlisted services can be queried. However, it never states when to prefer this over siblings like health, uptime, or tail_logs, nor what happens for non-allowlisted services.

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 a security behavior (allowlist enforcement, path traversal rejected), which is real value beyond the schema. However, it says nothing about error behavior on rejection, output size limits, or whether the allowlist is fixed or configurable.

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 sentence with the key constraint front-loaded and no wasted words. It is arguably over-terse for a 2-param tool, but nothing is padded.

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, which keeps the bar lower. Still, for a tool whose only parameters are undocumented, the description should cover how path is validated and how the line count is applied; those gaps remain.

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% with two parameters. The phrase 'final lines' hints at the lines parameter but never names it, gives no default behavior, and the required path parameter is only indirectly referenced via the allowlist language. Documentation of parameters is left almost entirely to the untyped 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?

States a specific verb (read) and resource (final lines of a log file) plus an important scope qualifier: one exactly allowlisted file. An agent can immediately tell this is a constrained log-reading tool, though it does not explicitly differentiate itself from siblings like health or service_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?

No when-to-use guidance, no mention of alternatives, and no stated preconditions beyond the allowlist constraint. The diagnostic context is only implied; the agent gets no help deciding between tail_logs and evidence_snapshot or service_status.

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 load, and it does disclose the mechanism ('standard uptime command'), which implies a safe, read-only local invocation. However, it says nothing about required permissions, execution environment, or the fact that load-average semantics are platform-dependent.

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 that front-loads the returned resource and adds the one useful detail (the underlying command) with no padding. 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?

Because an output schema exists, the description need not spell out return fields, and the tool is trivially simple with no arguments. The only real omission is when to prefer it over the overlapping health 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 tool takes zero parameters, so there is no parameter semantics to document; the baseline for a no-argument tool is 4. Nothing in the description misleads about inputs.

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

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

Specific verb (Return) and resource (host uptime), which cleanly distinguishes it from siblings like memory, disk_usage, and health. It does not explicitly contrast itself against the closest sibling (health), 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?

No indication of when to reach for this tool versus alternatives such as health or evidence_snapshot, and no preconditions or context given. The description only states what it returns, not when it is the right choice.

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