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

With no annotations, the description carries the full burden and does substantial work: it names the engine (Whisper), discloses the three write targets in the graph, and explicitly documents best-effort failure semantics ('ingested' is None when no engine is reachable). What it omits is whether re-ingesting the same audio creates duplicate nodes and what permissions the graph writes require — meaningful gaps for a multi-node mutation, but the disclosed behavior is well above average.

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?

Front-loaded with the core action, then structured detail on outputs and failure mode. Every sentence carries information; only the trailing 'CONCEPT:AU-KG.ingest.enterprise-source-extractor' token is noise an agent cannot act on.

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 return shape need not be explained, and the description covers inputs, engine, write targets, and degraded-mode behavior. For a tool that mutates a knowledge graph, the remaining unanswered question — idempotency/duplicate handling on re-run — is the one notable omission.

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

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

Schema description coverage is 100%, so task, model, language, and audio_file are all self-documenting and the baseline is 3. The description adds a little framing by stating Whisper runs specifically on ``audio_file``, confirming that this is the source media path (audio or video) rather than a derived artifact, but it adds nothing on task/model/language tradeoffs.

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 pair (transcribe + ingest) and a specific target (the knowledge graph), then enumerates the exact artifacts produced: an :AssetOccurrence blob, a :Document, and :TranscriptSegment nodes. 'Natively ingest it into the knowledge graph' implicitly separates it from plain transcription siblings like transcribe_audio, so an agent can tell what makes this one different without opening any 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?

The description conveys that this is a transcription-plus-ingestion operation, which implies its use case, but it never says 'use this when you need the result stored, otherwise use transcribe_audio/audio_transcriber_transcribe.' No prerequisites, no exclusions, and no guidance on repeat invocations or when a lighter sibling is preferable.

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=false, openWorldHint=true, and destructiveHint=false, so the safety profile is partly covered. However, the description adds no behavioral context such as whether it writes a file, returns exported content, requires a completed transcription, or supports specific output destinations. For an export operation with a free-form result object, this is a significant 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?

The description is a single short sentence with no wasted words and is front-loaded. It is appropriately sized, though its brevity comes at the cost of detail rather than being a model of efficient completeness.

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 two required parameters, a nested 'result' object, no output schema, and only partial annotations, the description is too thin. It omits supported formats, expected result structure, output behavior, and distinctions from sibling transcription tools.

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 but does not. It only vaguely references 'formats' and says nothing about the required 'result' object or accepted format values, leaving both required parameters largely undocumented.

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 ('Export transcription') and distinguishes it from transcription and streaming siblings. It is clear what the tool does at a high level, though 'specified formats' leaves the supported formats unspecified.

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 siblings like transcribe_audio or audio_transcriber_save_stream, nor any mention of prerequisites or alternative workflows. The agent must infer the correct usage context.

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 declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, implying an external-resource setup step, but the description adds nothing beyond that — no mention of device permissions, resource allocation, or what happens if a stream is already open. Given the openWorld hint, the description should clarify the side effects of opening an external capture stream.

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 sentence with no wasted words and is front-loaded, but the brevity comes at the cost of under-specification rather than genuine efficiency.

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 stateful stream-lifecycle tool with no parameters and no output schema, the description leaves the agent without the essential context: what the stream captures, what state changes occur, and which sibling to call next (stop_stream/save_stream). It is not complete enough to call correctly with confidence.

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; the baseline of 4 applies. The description does not mislead 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?

The description says 'Initiate the audio input stream', which gives a verb and a resource, but the resource is only vaguely identified — it is unclear whether this opens a microphone, a file, or a network stream. It does not distinguish this from siblings like audio_transcriber_record or audio_transcriber_stop_stream.

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 this tool should be used instead of audio_transcriber_record, nor any mention of the required follow-up (stop_stream / save_stream). The agent must infer the whole stream lifecycle from sibling names alone.

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

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

Annotations already declare readOnlyHint=false, openWorldHint=true, destructiveHint=false, so the network-bound, non-destructive-write profile is covered externally. The description adds only "via WebSocket," but says nothing about session persistence, whether the connection is left open, what authentication or message protocol the PersonaPlex server expects, or what a call blocks on. For an open-world interactive tool this is 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 short sentence with no padding, which is structurally fine, but the brevity comes from under-specification rather than efficiency. Nothing is wasted because almost nothing is said.

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 no output schema and one undocumented parameter, the description is the only source for what an "interaction" consists of, and it fails to supply it. The agent does not know whether to expect a stream of audio, a text reply, or a session handle, nor how the call terminates.

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 server_url has no description in the schema, so the description should compensate — instead it just names "PersonaPlex server" without giving a URL format, scheme/port example, or whether ws:// vs wss:// is expected. It adds only marginal meaning beyond the parameter name.

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?

"Interact with PersonaPlex server via WebSocket" essentially restates the name (audio_transcriber_interact) and title (Interact) and swaps in the transport mechanism. It names no concrete operation — no audio sent, no messages received, no session lifecycle — so an agent cannot tell what this does that audio_transcriber_initiate_stream or audio_transcriber_save_stream do not.

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, no preconditions (must a stream be initiated first?), and no mention of the nine sibling tools it overlaps with. The agent must guess 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?

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds almost nothing beyond that: it never says where the audio is written, whether a mic/permission is needed, whether it blocks, or what a duration of 0 does. For a capture tool with a live external dependency, that 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?

One short sentence, front-loaded with the verb and resource, with no wasted words. It is concise but arguably under-specified rather than tight.

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 no output schema and an undocumented optional parameter, the description should explain the return (path, handle, or transcription trigger) and the default/stop behavior. It omits both, leaving an agent unable to predict the result of the call.

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 explain the single parameter. 'Specified duration' loosely maps to `seconds`, but it never states units, the default of 0, or that 0 means record until explicitly stopped — the most important semantic of the parameter.

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 ('Record audio') plus its termination condition, which distinguishes it from sibling transcribe/stream tools. It does not explicitly name which sibling to use instead, so it falls short of the top tier.

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 audio_transcriber_initiate_stream or audio_transcriber_stop_stream, which operate in the same domain. The 'or until stopped' clause hints at the stopping mechanism but never says how recording is actually stopped or what prerequisites exist.

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 disclose that this is a non-read-only, non-destructive, open-world operation, so the description does not need to restate that. It adds useful context by naming the output format (WAV), but it omits where the file is saved, whether existing files are overwritten, and what the tool returns.

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

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

The description is a single front-loaded sentence with no filler. It communicates the action and output format immediately.

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 simple zero-parameter tool, the description covers the core action and output format. However, as an open-world file-writing tool with no output schema, it should say more about the save location, overwrite behavior, and return value so the agent can call it confidently.

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 and the schema is fully described, so there is no parameter semantics for the description to compensate for. The baseline for a zero-parameter tool is 4.

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 output artifact: saving recorded frames to a WAV file. It is clear what the tool does, but it does not explicitly distinguish itself from sibling tools like audio_transcriber_export or audio_transcriber_stop_stream.

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 guidance on when to use this tool versus alternatives such as audio_transcriber_export or when recording must be stopped first. Usage is only weakly implied by 'recorded frames', leaving the agent to infer prerequisites and sequencing.

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=false and destructiveHint=false, so the safety profile is covered. The description adds that the stream is closed, implying it becomes unusable and resources are released, but it does not say whether buffered audio or untranscribed data is discarded — a key fact given the save/export siblings.

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 short, front-loaded sentence with no filler or repetition. It is arguably too terse for a lifecycle-terminating operation, but nothing in the text wastes space.

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 no parameters and no output schema there is little structural burden, and annotations cover the safety hints. However, for a stream-terminating tool the description omits what state changes on the server side and whether any pending audio is lost, which an agent needs in order to sequence it correctly relative to save/export.

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. Schema coverage is 100% and no argument interpretation is required.

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 (stop) and resource (the audio stream) plus the additional closing action, which clearly pairs against the sibling 'audio_transcriber_initiate_stream'. It does not explicitly disambiguate from save_stream/export beyond the plain meaning of 'stop', but an agent can identify the operation 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?

Usage is only implied by the lifecycle pairing with initiate_stream; there is no statement of when to call this versus saving or exporting the stream first. The existence of audio_transcriber_save_stream and audio_transcriber_export makes that ordering decision non-trivial, and the description stays silent on 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=false and openWorldHint=true, so the safety profile is covered. The description adds nothing beyond that: it doesn't say what the backend must be initialized with, whether transcription is synchronous or long-running, what the output looks like, or what happens on failure.

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 short, front-loaded sentence with no filler, so it isn't bloated. But brevity here reflects under-specification rather than economy, given the tool's complexity.

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 7-parameter transcription tool with no output schema, no annotated output description, and no parameter documentation in either schema or description. The description does not give the agent enough to call this correctly.

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?

There are 7 parameters with 0% schema description coverage, and the description mentions none of them. Key options like task ('transcribe' vs presumably 'translate'), language, word_timestamps, initial_prompt, and temperature are left entirely 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?

The description names a specific verb and resource ('Transcribe the audio file'), but says nothing that distinguishes it from the many sibling transcription tools (transcribe_audio, transcribe_media_transcribe_segments). 'The initialized backend' hints at server state but doesn't clarify scope or output.

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 pick this tool over transcribe_audio or transcribe_media_transcribe_segments, and no explicit statement that initialization must happen first (only implied by 'initialized backend'). The agent must guess the ordering and the alternative.

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, so the safety profile is covered. The description adds genuinely useful context beyond them: what is actually inspected (importable Whisper backends, ffmpeg on PATH, default model, transcription directory) and the explicit absence of model loading, which matters for cost/latency. It stops short of saying anything about failure modes, e.g. what is reported when ffmpeg is missing.

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 paragraphs, front-loaded with the key differentiator ('without loading a model') followed by the concrete list of what is inspected and a closing reassurance ('Changes nothing'). 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 and annotations carry the safety profile, so the description need not explain return values or side effects. It covers what an agent needs to select and invoke this zero-argument diagnostic tool correctly.

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?

Zero parameters, so the baseline is 4 and there is nothing the description could add or omit 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?

Specific verb (report) plus specific resource (the transcription engine's state), with an explicit qualifier 'without loading a model' that separates it from every transcribe_* sibling. An agent can distinguish it from transcribe_audio without consulting 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?

The phrase 'without loading a model' signals the cheap check-first use case versus the heavier transcription siblings, though no sibling is named explicitly and there is no explicit 'call this before X' instruction. Clear context, but alternatives are implied rather than spelled out.

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 idempotent=true, destructive=false and openWorld=false, so the safety profile is covered. The description adds the useful behavioral fact that input can come from a file or live microphone, but says nothing about where exports are written, whether the call blocks during recording, or microphone permissions.

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 zero padding. It is efficient, though it borders on under-specification for a 12-parameter tool rather than being genuinely concise in a way that helps.

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?

This is a 12-parameter tool that can record from a microphone and write exported files, yet the description never explains the required source combination, where output lands, or call duration behavior. An output schema and annotations exist, but they cannot cover source-selection rules or side-effect semantics the agent needs before calling.

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

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

Schema description coverage is 100%, so all 12 parameters are documented in the schema; baseline 3 applies. The description only reinforces the audio_file vs record_seconds distinction and adds no format, default, or interaction detail beyond the schema.

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

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

States a specific verb+resource ('transcribes audio') and two source modes, so the basic action is clear. However, with siblings like audio_transcriber_transcribe, audio_transcriber_record and audio_ingest_transcription, the description gives no hint why an agent would pick this tool over those, so the purpose is only minimally distinguished.

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 the many transcribe/record siblings, no prerequisites, and no exclusions. The only implied usage is the mutually exclusive file-vs-microphone source, which is left for the agent to infer.

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?

Usefully discloses behavior the annotations do not: it never raises, every failure returns {available: False, error: ...}, and it follows a 'never fabricate' sidecar-delegate contract. That is real error-model context. It stops short of explaining permission requirements, idempotency implications (annotations say idempotentHint=false), or cost/latency of Whisper calls.

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

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

Front-loaded with the action and kept to two sentences, with the failure contract placed after the core purpose. Dense backtick/RST-style formatting ('AudioSegment-shaped', double backticks) slightly reduces readability 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?

With an output schema present, the description needn't explain return values, yet it still names the segment fields and, more importantly, the failure envelope. For a single-parameter, non-destructive transcribe call this is close to sufficient; only sibling differentiation and invocation prerequisites are 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 coverage is 100% and the single params_json field already enumerates digest, media_type, artifact_b64, language, task, word_timestamps. The description's mention of 'verify the digest' hints at the digest parameter's role but adds no format or constraint detail beyond the schema.

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

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

The description gives a specific verb and resource ('Transcribe segments') and names the underlying delegate ('transcribe_media'), plus the concrete output shape (start_ms/end_ms/text). It does not, however, distinguish this from close siblings like transcribe_audio, audio_transcriber_transcribe, or audio_ingest_transcription.

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 prefer this over the many sibling transcription tools, nor any exclusion or prerequisite guidance beyond 'verify the digest'. The agent must infer routing 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.