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

With no annotations, the description fully discloses behavior: returns verbatim spans, never summaries, reports dropped coverage, uses Intel NPU embedding, writes nothing to semantic index, and has file size limits (4KB-256KB). It also notes it does not substitute for grep. This is comprehensive transparency without annotation support.

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 well-structured: purpose, usage guidance, example, output behavior, technical details, constraints. Each sentence carries useful information; no filler. It is longer than average, but justified by the tool's complexity and the absence of annotations.

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

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

Given the tool's complexity (NPU-based embedding, filtering, output reporting), the description covers purpose, use cases, alternatives, constraints, privacy, and output format. There is no output schema, but the description clearly explains the returned data: verbatim spans with line numbers and dropped-score statistics. Missing parameter documentation is a minor gap, but the overall context is complete.

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

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

Schema coverage is 0%, and the description mentions only the two required parameters (path and query) via example, plus 'limit' implicitly ('raise limit'). The parameter context_lines remains undocumented in both description and schema. The description adds some meaning beyond the schema, but not enough to fully compensate for the 0% 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 clearly states 'Extract only the parts of a large local text file that are relevant to a question.' This is a specific verb+resource (extract from file) and differentiates itself from grep and other sibling tools. The example invocation further clarifies its exact use.

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 explicitly says when to use it (instead of reading big logs, test output, diffs) and when not to use it: 'This is not a substitute for grep: when you know the exact string to look for, grep is faster, free, and exact.' It also suggests a workflow with tee and filtering, which provides clear 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?

Without annotations, the description carries the burden. The word 'Report' implies a read-only query, and no side effects are suggested. However, it does not explicitly confirm non-destructiveness, required permissions, or return format. For a simple status tool, this is adequate but not rich.

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

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

A single sentence of 12 words, front-loaded with the action verb 'Report'. Every word is necessary and the description is immediately scannable.

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, no-output-schema tool, the description fully specifies its sole function: reporting OpenVINO devices and Intel AI Boost availability. No additional context is needed for an agent to select and invoke it 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?

The tool has zero parameters, so per the rubric, baseline is 4. The description does not need to clarify parameter meanings because schema coverage is 100% (empty object) and no parameters exist.

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

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

The description uses a specific verb ('Report') and clearly identifies the resource (OpenVINO devices and Intel AI Boost availability). It distinguishes itself from sibling tools (which focus on transcription, OCR, and semantic indexing) by addressing a distinct hardware/software status topic.

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 for checking device status but does not explicitly state when to use it or when to avoid it. No alternatives are named, but given the tool's unique purpose, the context is reasonably clear and requires no exclusions.

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 of behavioral disclosure. It only mentions 'capture' and 'extract text,' but lacks details such as whether a screenshot is taken, if screen recording permissions are required, how the text is returned (e.g., string, file), or any side effects. This is a significant gap for a tool with no annotation support.

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 sentence of eight words, directly front-loaded with the action and outcome. Every word contributes to understanding. It is appropriately concise for a tool with no parameters and a simple action.

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

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

Given the tool's simplicity (no parameters, no output schema), the description provides a basic understanding of what it does and that it returns text. However, it omits important context such as whether the tool opens a UI or runs silently, how the extracted text is delivered, and any prerequisites (e.g., display access). It is minimally viable but lacks depth for a tool with no annotations or output schema.

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 empty with 100% coverage (trivially). With no parameters to describe, the description does not need to add parameter information. The baseline for no-parameter tools is 4, and nothing in the description detracts from that.

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 states the tool's action: capture the current monitor and extract its text. This distinguishes it from sibling tools like ocr_image, which likely processes a specified image, and transcribe_audio, which handles audio. The verb 'capture' is specific in context, implying a screen capture.

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: when you want to extract text from the current screen. However, it does not explicitly state when to use this tool versus alternatives like ocr_image or open_ocr_selector, nor does it provide any exclusions or prerequisites. Basic implied usage only.

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 for behavioral disclosure. It adds context 'using NPU text models', but fails to mention what the extracted text looks like (return format), whether it is synchronous, supported image formats, or failure behavior. This is insufficient for a zero-annotation tool.

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

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

The description is a single, front-loaded sentence that directly states the core function. Every word adds value, with no filler or redundancy. It is appropriately sized for a one-parameter 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 no output schema and only one parameter, the description should clarify what the function returns. 'Extract text' implies returning text but does not specify whether it is a plain string, a list of segments, or includes confidence scores. No mention of prerequisites like NPU support or image format constraints also leaves 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 coverage is 0%, so the description must compensate. It indirectly hints that image_path refers to a local image, but does not specify path format, acceptable image extensions, file size limits, or whether the path is relative or absolute. This adds marginal meaning beyond the schema's simple 'Image Path' label.

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 states the verb 'Extract' and the resource 'text from a local image', specifying supported languages (English and Arabic) and method (NPU text models). This distinguishes it from siblings like ocr_current_monitor (which targets the current monitor) and transcribe_audio (which handles 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?

Usage is implied through 'local image' which contrasts with the monitor-based sibling ocr_current_monitor, but there is no explicit guidance on when to choose this tool over alternatives or mention of prerequisites. The description does not provide exclusions or alternative tool references.

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 of behavioral disclosure. It merely restates the tool's name ('Open...selector') without explaining what 'open' entails, whether it returns a selection, blocks, or has side effects. This adds no value beyond the name itself.

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, front-loaded sentence that states the purpose efficiently. No wasted words or redundant content.

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

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

Given the tool has no parameters and an output schema exists (which likely documents return value), the description minimally suffices. However, it lacks any workflow context about how this selector fits with sibling OCR tools, leaving the agent without guidance on when to call it. It is a viable but incomplete description.

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 is 4. There is no additional parameter information needed; the description correctly omits param details since none exist.

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 states the tool's function with a specific verb ('Open') and resource ('rectangular screenshot OCR selector'). It distinguishes this tool from the sibling OCR tools like ocr_image and ocr_current_monitor, which perform OCR on already-acquired images rather than opening a selection UI.

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 provides no guidance on when to use this tool versus the alternatives. It does not mention that this selector is likely a prerequisite for other OCR tools or that it should be used before capturing a screenshot region. No exclusions or alternative suggestions 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?

With no annotations, the description carries full responsibility for behavioral disclosure. It only says 'Open', but does not explain whether the application launches asynchronously, requires user interaction, or what the output/return value represents. This is a significant gap for a tool with no annotation support.

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, clear sentence with no redundant information. It is appropriately sized for a parameterless tool and front-loads the actionable verb.

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?

While the tool is simple and has an output schema, the description does not clarify what outcome the agent can expect (e.g., success message, process launch, or UI opened). The lack of annotations and usage guidance leaves some contextual gaps, but complexity is low enough that this is minimally adequate.

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 schema already provides complete coverage (100%). The description adds no parameter details, but none are needed; a baseline of 4 is appropriate for parameterless tools.

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 states the action ('Open') and the target resource ('interactive speech-to-text desktop application'). It is unambiguous and distinct from sibling tools that handle transcription or OCR operations.

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 is provided about when to use this tool versus alternatives. It does not mention prerequisites, typical scenarios, or exclusions, leaving the agent to infer usage from the name and description 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?

No annotations are provided, so the description carries the transparency burden. It discloses the duration range and NPU-based processing, but it does not describe output format, error handling, microphone permissions, or whether the recording is saved. These are notable gaps for a recording 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?

The description is a single, clear sentence that conveys the tool's purpose, duration limit, and hardware context without redundancy. It is front-loaded and easy to parse.

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

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

Given the presence of an output schema and only one simple parameter, the description covers the core functionality and duration range. Minor gaps exist in usage guidance, but overall it is complete enough for an agent to understand the tool's role.

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 input schema has a single undocumented parameter 'seconds' with a default of 10. The description adds crucial semantics by specifying the allowed range of 1-60 seconds, which is not present in the schema. This directly clarifies parameter meaning and constraints.

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 states the tool records from the default microphone for 1-60 seconds and transcribes on the NPU. It uses specific verbs ('record', 'transcribe') and identifies the resource ('default microphone'), distinguishing it from siblings like 'transcribe_audio' (which only transcribes) and 'npu_status' (which checks hardware).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: the tool is for recording and transcribing audio in one step. However, it does not explicitly mention when to use this vs. alternatives like 'transcribe_audio' for existing audio files, nor does it provide exclusions or prerequisites.

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

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

With no annotations provided, the description carries full responsibility and delivers thoroughly. It discloses that output is from Tesseract OCR (best-effort, not a UI tree), lists specific limitations (cannot report widget types, enabled/checked state, focus, scroll position, off-screen content, misreads small/low-contrast text), and warns that the 'words' detail can cost more tokens than a screenshot. This goes well beyond the minimum.

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 appropriately sized given the tool's complexity. It front-loads the core purpose in the first sentence, then efficiently covers cost motivation, parameter details, limitations, and alternatives in a well-structured flow. Every paragraph earns its place, and there is no fluff or redundancy.

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

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

Given no annotations or output schema, the description covers purpose, usage, limitations, return format (reading order text with bounding boxes), and parameter semantics for most parameters. The only gap is min_confidence, which is left unspecified. Despite this, the description is largely complete for an agent to use the tool safely and effectively.

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 schema has no descriptions (coverage 0%), so the description must compensate. It does for two of three parameters: detail (explains 'lines', 'text', 'words' with trade-offs) and image_path (explains omission captures the monitor). However, min_confidence is never mentioned, so the agent is left guessing what it controls. This slight omission prevents a perfect score.

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

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

The description opens with a clear, specific action: 'Read a screenshot as compact structured text instead of sending an image.' It specifies the resource (screenshot/image) and the output (structured text with bounding boxes). It also distinguishes itself from sibling tools like ocr_image and ocr_current_monitor by framing it as a token-saving alternative and contrasting with Playwright's accessibility tree.

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?

Explicitly states when to use this tool: for surfaces without an accessibility tree (native desktop apps, remote desktops, canvas/WebGL, video frames, scanned documents). It gives a clear alternative: 'If the target is a web page, use Playwright's accessibility tree instead' and explains why. It also provides operational guidance on omitting image_path to capture the current monitor and how to choose the detail level.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does not mention whether the operation is destructive, requires specific permissions, modifies existing indexes, or what the output looks like. The phrase 'Index a local text file or directory' hints at reading files and creating an index, but side effects are not 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?

The description is a single sentence, front-loaded with the verb and resource, and contains no filler. Every word earns its place.

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

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

The tool has no output schema and no annotations, so the description is the only source of information. It does not explain what the tool returns, whether it can be run repeatedly, or how the index integrates with semantic_search. While the tool has only one parameter, key operational details 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?

The schema describes 'path' only as a string, but the description adds that it should be a local text file or directory, which clarifies the expected input. This compensates for the 0% schema description coverage, though it could specify supported file types or recursion 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 states the tool's action ('Index') and resource ('local text file or directory'), and specifies its purpose ('for private semantic search on the Intel NPU'). It distinguishes from siblings like semantic_search, which searches, and semantic_index_status, which checks 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?

The description implies that this tool should be used before semantic_search to build an index, but it does not explicitly state when to use it vs alternatives or mention any prerequisites or exclusions. It provides context but no direct guidance on choosing between 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?

With no annotations provided, the description carries the burden. The verb 'Report' clearly indicates a read-only, non-destructive operation. While it does not disclose edge-case behaviors (e.g., what happens if the index is missing), the zero-parameter read-only nature is transparent and adequate for this 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?

The description is a single, concise sentence that front-loads the action ('Report') and immediately lists the data items. No filler or redundant wording. Every word adds value.

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 (0 params, no output schema), and the description lists the key outputs (database, roots, file count, chunk count). It gives a clear picture of what to expect from the tool. It does not specify the return format, but for a status tool this is a minor 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?

The tool accepts zero parameters, so there is no parameter ambiguity. The description fully covers the tool's inputs by having none. According to the rubric, a baseline of 4 is appropriate for 0-parameter tools.

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

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

The description uses the specific verb 'Report' and clearly identifies the resource (local semantic index database) plus the exact items being reported (roots, file count, chunk count). It distinguishes itself from sibling tools like semantic_index or semantic_search by focusing on status/read-only reporting.

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 for checking the state of the semantic index, but does not explicitly state when to use it relative to alternatives (e.g., before indexing or searching). No exclusions are mentioned, but the purpose is self-evident enough to warrant a mid-range score.

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 behavioral disclosure burden. It transparently explains the optional reranker, the unbounded logit nature of rerank_score, and the time tradeoff. It does not cover the full return structure, but the output schema fills that 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 compact and front-loaded: the purpose is in the first sentence, followed by a caveat paragraph that adds behavioral nuance. No sentence 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?

Given the presence of an output schema, the lack of annotations, and moderate complexity, the description covers the core purpose, a key behavioral caveat, and an implicit prerequisite. It could add more detail about root and limit, but overall it is sufficiently complete for selection and initial invocation.

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

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

Schema description coverage is 0%, so the description must compensate. It provides rich semantics for the rerank parameter (what rerank_score is, how to disable it), but leaves root and limit unexplained beyond their names; query is implied by 'search'.

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

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

The description opens with a specific verb and object: 'Search indexed local files by meaning using Intel NPU embeddings.' This clearly distinguishes the tool from siblings like semantic_index and semantic_index_status, and states the method of search.

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 'indexed local files' implies the tool is used after indexing and for semantic rather than keyword search. It also provides conditional guidance for reranking ('Pass rerank=false to skip the extra second of work'), though it doesn't explicitly name alternative tools for exclusion.

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 must disclose behavior. It mentions 'local' and 'Intel NPU' which are valuable constraints, but does not disclose potential side effects, required permissions, or limitations like supported audio formats.

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 entire description is a single sentence with 8 words, focusing directly on the action. There is no redundant 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 with one parameter and an output schema, so the description covers the essentials. It lacks details on file formats or hardware requirements beyond the NPU, but given the low complexity, it is reasonably complete.

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 schema provides only the parameter name 'Audio Path' with no description. The description clarifies that the parameter is the path to a local audio file, adding meaning about its nature and locality.

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

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

The description uses a specific verb 'Transcribe' and identifies the resource as 'a local audio file', distinguishing it from siblings like 'record_and_transcribe' which implies recording first. The hardware detail 'on the Intel NPU' also adds specificity.

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 existing local files, but does not explicitly mention alternatives or when not to use it. Sibling 'record_and_transcribe' suggests a related but different workflow, but no comparison is made.

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