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 establish the non-mutating contract via 'Markiert nichts' and enumerates the returned fields, but says nothing about permissions, pagination, or what the single parameter controls.

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 compact sentence with the resource front-loaded and the field list in parentheses; nothing is padded. It is terse to the point of omitting the one parameter, but no wording 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?

Because an output schema exists, the description needn't explain return values, which offsets some of its brevity. However, for a tool with zero annotations and an undocumented input parameter, more behavioral and parameter context was warranted.

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 one parameter 'ab' has 0% schema description coverage and is not mentioned in the description at all, so the agent cannot tell whether it is an offset, a mailbox index, or a filter. This is the definition's largest gap given the parameter is optional and defaults to 0.

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 the resource (Anrufbeantworter) and states it returns status plus messages with the concrete fields Zeit, Anrufer, Dauer, neu/gehört. That is specific enough to distinguish it from anrufliste, though it never explicitly rules out the audio sibling anrufbeantworter_audio.

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?

'Markiert nichts' functions as a partial exclusion, hinting at a counterpart that does mark messages as heard, but no sibling is named and no condition for choosing this tool over anrufliste or anrufbeantworter_audio is given. Usage is only implied by the read-only framing.

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 must carry the whole behavioral burden. It usefully discloses that a file is written to FRITZ_DOWNLOAD_DIR and that the message's "heard" state is NOT changed, but says nothing about permissions or remote-access prerequisites, filename/path resolution, or what happens if the message index is invalid.

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, purpose front-loaded, with the notable non-side-effect placed second. 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?

An output schema exists, so return values need not be described, and the tool is low-complexity with only two parameters. However, for a tool that writes to disk, the undocumented 'ab' parameter and absent error/prerequisite information leave meaningful gaps.

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 had to compensate and largely does not. "Nachricht" is inferable from "AB-Nachricht", but the 'ab' parameter (which answering-machine mailbox, default 0) is never mentioned, leaving a required-shaped integer completely 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 ("Lädt") plus resource ("AB-Nachricht als WAV") and the destination (FRITZ_DOWNLOAD_DIR), which is far more informative than the tool name alone. It does not explicitly distinguish itself from the sibling 'anrufbeantworter' (listing) tool, so it stops 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?

Usage is only implied: fetch a message's audio. The sentence "Markiert nichts als gehört" hints that a different tool/step is needed to mark as heard, but no alternative is named and no preconditions 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?

No annotations are supplied, so the description carries the full disclosure burden, and it discloses almost nothing: neither read-only/safety character, nor whether results are ordered or paginated, nor what the default limit of 30 implies. Only the 'letzte n Tage' recency constraint hints at behavior. For a tool with zero annotation coverage this is a substantial 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 telegraphic fragments carry a fair amount of information with no filler, and the filter details are front-loaded. But the leading 'Anrufliste.' merely restates the tool name and the fragmentary, punctuation-light style makes the key/value mapping harder to parse than a single clean sentence would.

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, and all three parameters are optional, keeping the call surface simple. Still, the undocumented 'limit' parameter, its default of 30, and the nullable 'art'/'tage' semantics leave real gaps for an agent deciding how to control result size and filtering.

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 description genuinely adds the allowed values for 'art' (eingehend | verpasst | ausgehend | blockiert | AB), which the schema only types as a bare string. However, 'limit' (default 30) is completely undocumented and the interaction between 'art' and 'tage' plus what a null 'art' means are left unstated, so it only partly compensates 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 names the resource ('Anrufliste') and enumerates the call categories it covers (eingehend, verpasst, ausgehend, blockiert, AB), which tells an agent this is a call-history listing with type-based scoping. It is terse and noun-only, and it does not distinguish the tool from the closely related sibling anrufbeantworter, but the scope is inferable without opening the schema.

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 use this tool versus the siblings anrufbeantworter, anrufbeantworter_audio, or protokoll, even though 'AB' in the type list clearly overlaps with the answering-machine tools. Usage is only implied by the resource name; no prerequisites, exclusions, or alternatives are 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?

No annotations are supplied, so the description carries the full disclosure burden, and it discloses almost nothing behavioral. It does not state that this is a read-only query, whether it requires an established DSL connection, whether the values are instantaneous or averaged, or how it behaves during a sync loss — all relevant for a line-status 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?

It is a single short fragment with no wasted words, but it is terse to the point of under-specification — a colon-delimited keyword list rather than a sentence. Front-loading the resource is good, but the phrasing reads like a label, not guidance.

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?

A zero-parameter read with an output schema means the return values need no explanation, so the bar is low and the field list is largely sufficient for calling it. Still, with no annotations and no usage framing, an agent gets no signal about when this tool is the right pick among the ten 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 nothing for the description to clarify beyond the schema; baseline 4 applies. The listed metric names are context about the return payload rather than parameter meaning, which is a reasonable use of the space.

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 is a noun phrase listing the DSL line's reported metrics (Sync, Maximalrate, Marge, Dämpfung, CRC/FEC) rather than a verb+resource statement, so the action (fetch current status) must be inferred from the tool name. It does, however, identify the resource and distinguish the content from siblings like wlan_status or mesh_uebersicht by naming DSL-specific fields.

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 indication of when to use this tool instead of zugang_pruefen, protokoll, or the other status-oriented siblings. No prerequisites, no exclusions, and no note that this reports live link metrics rather than diagnostics history.

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 implicitly signals a read-only lookup and names the fields returned, but says nothing about matching semantics (exact vs. partial, case sensitivity), behavior on zero matches, or any permission requirements. Adequate for a low-risk read, but incomplete for a no-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?

Two short, front-loaded sentences with zero filler: the question establishes intent, the colon list enumerates search keys and result fields. Nothing could be removed 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?

For a one-parameter lookup with an output schema (so return structure needn't be explained), the description covers intent, accepted input formats and a hint at returned fields. The remaining gap is match semantics and not-found behavior, which is minor at this complexity level.

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 parameter 'suche' is an undocumented string. The description compensates well by defining the accepted value space: name, IP address, or MAC address. It stops short of stating whether partial or fuzzy matches are accepted.

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 question ('Wo hängt ein Gerät?') and the lookup keys (Name, IP, MAC) plus what is returned (Zugangspunkt, Band, Signal, Raten). That is a concrete verb+resource pair an agent can act on. It does not explicitly distinguish itself from the sibling 'hosts', which likely also enumerates devices, so sibling differentiation is left to inference.

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 by the question form: use this when you need to locate a specific device on the network. There is no explicit when-to-use/when-not guidance and no mention of 'hosts', 'wlan_status' or 'mesh_uebersicht' as alternatives for listing or checking connectivity.

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 only weakly implies a read-only inventory operation. It does not clarify whether device state is live or cached, whether inactive devices are included by default, or whether results can be truncated.

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 compact phrase is easy to scan and puts the resource and principal data fields first, with no filler. Its brevity is efficient, although it leaves several operationally useful details unstated.

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 reduces the need to document return fields, and the tool itself is relatively simple. Nevertheless, the complete absence of parameter documentation, behavioral context, and sibling differentiation leaves substantial gaps for correct selection and 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%, and the description does not explain any of the three parameters. In particular, it never states that name filters devices, nur_aktive restricts results to active devices, or limit caps the result count; the mention of aktiv/inaktiv describes device data rather than filter behavior.

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

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

The description clearly identifies an inventory of known devices on the box and specifies IP, MAC, active/inactive state, and connection type as the available data. It does not explicitly state a listing verb or differentiate this overview from the sibling tools geraet and mesh_uebersicht.

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 implicitly suggested when an agent needs an overview of known network devices and their connection details. There is no explicit guidance on when to choose hosts over geraet for an individual device or mesh_uebersicht for mesh topology.

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 supplied, so the description carries the full burden; it does imply a passive read by describing only returned attributes, but it never says the call is non-destructive or side-effect free. Nothing about what happens when no mesh nodes exist, whether data is cached/polled, or any rate/permission constraints is disclosed.

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 dense sentence front-loads the resource and then lists the returned facets without filler. Every clause maps to real content an agent would care about.

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-argument read tool with an output schema and no annotations, the description covers scope and the shape of the result, which is essentially enough to call it. The only shortfall is the missing routing hint relative to wlan_status and zugang_pruefen.

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, which is the baseline-4 case; the schema is also fully described. The description correctly adds no parameter guidance because none is needed, and instead spends its words on the reported fields.

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 resource scope ('Alle Mesh-Zugangspunkte') and enumerates exactly what is reported per access point (role, uplink rates, channel/bandwidth/utilization per radio, client count), so an agent can tell this is the mesh-topology inventory. It does not, however, distinguish itself from the nearby wlan_status or geraet siblings, and the verb ('list/return') stays 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 statement of when to reach for this over wlan_status (single-radio WLAN state) or zugang_pruefen (access check), and no preconditions or exclusions. The agent must infer usage purely from the noun phrase.

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 discloses ordering (newest first), which is genuinely useful, but says nothing about read-only nature, pagination behavior, the default limit of 50, retention window, or result size.

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?

Compact and front-loaded with the resource and ordering first. But the terseness tips into under-specification rather than efficiency; the fragment style leaves the agent to guess at semantics.

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 explained. Still, a 3-parameter tool with zero annotations and zero schema coverage deserves more than one fragment — the limit parameter and the overall read semantics are undocumented.

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 does add real meaning for two of three parameters ("seit" is an ISO date/time bound, "stichwort" is a text filter), but "limit" is never mentioned, leaving the truncation behavior 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?

Names the resource ("Box-Protokoll") and its ordering ("neueste zuerst"), which lets an agent distinguish it from siblings like dsl_status or anrufliste. However, there is no verb — it never says it lists or returns log entries — so the purpose is implied rather than stated.

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 exclusions, and no mention of alternatives among the many sibling status tools. The agent must infer that this is the router event log rather than a device or call log.

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 discloses the scope of data covered (bands, guest network, on/off, SSID, channel, auto-channel, connected devices), which is useful behavioral context, but it does not state that the operation is read-only, nor does it mention permissions, side effects, or rate 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?

The description is a single compact phrase with the resource front-loaded and no wasted words. It is efficient but fragmentary, lacking a verb that would make the intent immediately unambiguous.

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 status tool with an output schema, the description is largely sufficient: it scopes which WLAN aspects are covered and notes guest-network and device coverage. The main gap is the absence of any read-only or safety framing, which matters more because no annotations 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 the baseline of 4 applies. The description adds no parameter meaning because none exist, which is appropriate.

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

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

The description names a specific resource – the box's WLAN radio components across 2.4 GHz, 5 GHz and guest networks – and enumerates the attributes covered (on/off, SSID, channel, auto-channel, devices). It is clearly distinguishable from siblings like dsl_status or mesh_uebersicht by resource, though it lacks an explicit verb such as 'returns' or 'reads'.

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 field list suggests it should be called to inspect WLAN status, but there is no explicit when-to-use guidance, no prerequisites, and no routing against related siblings such as dsl_status or mesh_uebersicht.

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 does disclose what is inspected (model, FRITZ!OS, user rights), which signals a non-mutating inspection. However, it says nothing about whether authentication is required, what a failed or insufficient-rights result looks like, or any side effects — the output schema covers the return shape but not the failure semantics.

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 fragment with zero filler, listing exactly the three things checked. Nothing could be removed 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?

The tool is simple (zero parameters), an output schema exists, and the description enumerates the returned subject matter, so an agent knows what it gets back. The only shortfall is the absence of guidance on when to invoke it and how to interpret insufficient permissions.

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; the sentence adds no parameter noise and correctly implies the tool operates on the current session's box.

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 ('prüfen') with three concrete targets: box model, FRITZ!OS version, and the box user's permissions. This clearly separates it from the sibling tools (mesh_uebersicht, dsl_status, wlan_status, hosts, anrufliste), none of which report device model, firmware version, or access rights.

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 when-to-use guidance, no precondition, and no named alternative. The agent must infer that this is a pre-flight check before performing privileged operations, and nothing states what to do if the check fails.

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