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

With no annotations, the description carries the full burden, and it only partially does so: it discloses the return shape (side-by-side image plus changed-region pixel boxes in source coordinates), which is genuinely useful. It says nothing about whether this is read-only, whether it captures new frames or reads stored ones, or cost/latency for a visual operation.

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

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

A single front-loaded sentence with no filler; the output description is packed efficiently into the same line. Brevity is appropriate, though the terse phrasing contributes to the ambiguity noted elsewhere.

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?

Three required parameters at 0% schema coverage, no annotations, and no output schema mean the description should be doing much more. Describing the return value helps, but the missing parameter formats and safety profile leave an agent unable to call this correctly without guessing.

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% across three required params, so the description must compensate and largely doesn't. "Two moments" loosely maps to a and b, but their format (timestamp, frame ID, image reference?) is never stated, and watch_id is entirely unexplained.

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 verb and resource ("Compare two moments") and even describes the output shape (side-by-side plus highlighted pixel boxes). However, "moments" is undefined and nothing distinguishes this from siblings like frame, look, or image, so an agent can't confidently pick it over those.

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 or when-not-to-use guidance, and no mention of alternatives such as frame or look. The verb "compare" implies intent but the agent must infer the scenario and prerequisites entirely.

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 but says nothing about read-only behavior, side effects, permissions, or failure modes. It confirms that crop exists and is for small detail, but does not describe what state the call changes or what the return looks like.

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 text is brief and the crop detail is front-loaded, but 'Full-resolution frame at a time' is a fragment that reads more like a note than a complete purpose statement. It is concise but under-specified, forcing the agent to infer too much from a single sentence.

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 tool with 3 parameters, 2 required, 0% schema description coverage, no annotations, and no output schema, the description is far too thin. It explains crop but leaves the required timing parameter and the watch identifier completely 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 explain all three parameters. It does an excellent job on crop (pixel vs. fractional coordinates), but completely omits the required 'at' and 'watch_id' parameters, leaving their meaning and format unknown.

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 implies retrieving a full-resolution frame, but uses a noun phrase rather than a specific verb and never states what resource it operates on (a watch). It is distinct from siblings like zoom or image, but the core action is only inferred, not 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?

The only usage hint is 'for reading small detail,' which explains why crop exists but not when to choose frame over look, zoom, image, or images. No alternatives or exclusions are named, leaving the agent to guess.

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

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

With no annotations, the description carries the full burden and does well: it discloses that the no-region path returns a lettered grid plus EXIF, palette, and OCR-with-grid-cells, and that region requests return a native-resolution crop enlarged when small. It omits operational limits like max file size, auth, or whether source accepts data URIs/base64, leaving some behavioral gaps.

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 definition is front-loaded ('One image (file or URL)') and then cleanly splits the two modes with 'Without region...' / 'With region...'. Every clause contributes either coordinate format, output content, or usage rationale, with no filler.

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

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

For a 2-parameter, no-output-schema, no-annotation tool, the description covers both input semantics and the shape of returned content in each mode, which is most of what an agent needs. Minor gaps remain around source formats (data URI vs. path vs. URL) and image size limits.

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, and it does: it spells out accepted region syntaxes ('B2', 'B2:C3', 'x,y,w,h' in px or 0-1 fractions) and defines the default behavior when region is omitted. It also clarifies that source is a file or URL, giving meaning to both parameters beyond the bare 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 names a specific resource ('One image (file or URL)') and clearly delineates two operating modes: overview with a lettered grid + EXIF/palette/OCR, and native-resolution region extraction. It differentiates itself behaviorally (region zoom vs. full overview) but never explicitly contrasts against near-name siblings like 'images', 'zoom', or 'look'.

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?

It gives a clear use case: 'Use it to read small text in big screenshots and photos instead of guessing,' which tells the agent when this tool is the right pick. It does not name alternative siblings (e.g., 'zoom', 'look') or state when not to use it, so the guidance stops short of explicit routing.

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

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

No annotations are provided, so the description carries the full behavioral burden. It discloses return artifacts such as INDEX.md and a contact sheet, but omits important mutation details like whether an album is created or overwritten, permission requirements, reversibility, 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 two dense sentences and front-loads the indexing action and outputs. The second sentence shifts into sibling tool calls, which is useful context but slightly beyond what is needed to invoke this 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?

The description covers purpose, extracted metadata, and return values, which is helpful given there is no output schema. But with no annotations, no output schema, and an undocumented recursive parameter, album lifecycle and side effects remain incomplete for a tool that indexes images into an album.

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 usefully explains that sources can be folders, files, globs, or URLs, but it never mentions the recursive boolean, leaving one of two parameters without any semantic guidance.

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 action, 'Index images ... into an album,' and enumerates what is generated and returned. It also names follow-on sibling tools search, look, and image, making its role fairly clear, though it stops short of explicitly differentiating when this tool is preferred over those siblings.

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 a workflow: index sources into an album, then use search, look, or image for retrieval and detail. However, it does not explicitly state when to use this tool versus alternatives, nor does it list prerequisites or 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?

With no annotations, the description carries the full burden, and it does add real value by disclosing that results are cached and re-watching is instant. However, it does not clarify that this is a read-only enumeration, whether results are ordered or limited, or how it relates to starting a watch.

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 zero waste, and the core concept (previously watched videos) is front-loaded. It is arguably too terse rather than bloated, but structurally efficient.

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, and there are no parameters to document. Still, for a history-listing tool sitting among many viewing siblings, the description omits how it should be chosen over watch or live_watch_for, leaving a meaningful gap.

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

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

The tool takes zero parameters, so the baseline of 4 applies; nothing in the description is needed to explain inputs, and it introduces no misleading parameter expectations.

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 (previously watched videos) but uses a noun phrase with no explicit verb; the listing action is only inferable from the tool name. An agent can guess it returns watch history, but it isn't stated as 'list all watched videos' and there is no differentiation from siblings like watch or live_watch_for.

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 exclusions, and no reference to any of the many siblings (watch, live_watch_for, search, look). The agent must infer that this is the history-listing tool entirely on its own.

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 return composition (summary, latest frame, recent events), which is useful behavioral context, but omits whether the operation is read-only, how it behaves without a live session, or any permission/rate constraints.

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

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

A single efficient sentence with the key information front-loaded. No wasted words or unnecessary structure.

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

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

For a zero-parameter, no-output-schema tool, the description adequately explains what is returned. It could be slightly more complete by mentioning behavior when no live session exists, but it covers the essential return contents.

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 there are no parameter semantics to explain. Baseline 4 applies for a no-parameter tool.

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 resource and scope: current state of a running live session, including summary, latest frame, and recent events. However, it does not explicitly distinguish this tool from close siblings like live_snapshot or frame.

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 'right now' hints at temporal relevance, but there is no explicit guidance on when to use this tool versus live_snapshot, frame, live_watch_for, or other siblings. No exclusions or alternative tools are mentioned.

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

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

No annotations are provided, so the description carries full burden. It usefully discloses scope (capped at the buffer, ~120 s) and the produced contents (shots, text, speech, sound, Live signals), but omits whether a live session must be running, whether the snapshot is registered in list_watches, and what happens if `seconds` exceeds the buffer.

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 dense sentences with the core action front-loaded and the downstream capability stated second; little waste, though the parenthetical buffer note adds a mildly confusing default 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?

With no output schema, the description does a good job enumerating what the resulting watch contains and how it can be used downstream. The remaining gap is the lack of preconditions and the buffer/default ambiguity, which matter for a session-dependent tool.

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

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

Schema coverage is 0%, so the single `seconds` parameter depends entirely on the description. It explains that it selects the last N seconds capped by the buffer, but the claim '120 s by default' conflicts confusingly with the schema default of 30 and leaves the actual truncation behavior ambiguous.

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: turns the last `seconds` of the live session into a normal watch. That clearly separates it from siblings like live_watch_for and live_now, though those alternatives are never named explicitly.

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

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

The description gives clear context for use: convert buffered live footage so that 'All watch tools (zoom, frame, diff, search) then work on it', which names the follow-up tools. It does not state prerequisites (e.g., an active live session) or when to prefer live_now or live_watch_for instead.

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

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

With no annotations, the description carries the full burden and does well: it discloses background execution, optional monitor-page and OSC streaming, opt-in hands/pose cost, and a privacy guarantee (blendshapes and head pose, "no identities"). It omits failure modes such as a camera already in use or what happens on a second start.

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 source set, then the tracked signals, then the consent rule and next steps. Dense but nearly every clause adds usable information; the parenthetical affect and blendshape detail runs long.

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 spelled out, and the description covers sources, opt-ins, consent, and follow-up tools for a six-parameter tool. The unexplained mic parameter is the notable hole.

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 and largely does: source formats (camera, camera:N/name, screen:N, rtsp/srt/YouTube URL, file), watch_for with a concrete example, hands with pinch/gesture meaning, pose as body, and osc as output routing. The mic parameter and its "auto" default are never explained.

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 (start live perception in the background) and enumerates the accepted source types plus everything it tracks. It is clearly distinguished from live_now/live_snapshot/live_stop, which it names as follow-on tools, and from frame/watch style one-shot siblings.

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

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

Gives an explicit consent constraint ("Only start the camera or microphone when the user asked for it") and routes to the three follow-up tools. It does not name an alternative for non-realtime or one-shot needs, so it stops short of full when-not guidance.

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

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

No annotations are provided, so the description carries the full burden. It does well to disclose the concrete effects (camera, microphone and streams close), but says nothing about idempotence, behavior when no session is active, or whether the session can be resumed afterward.

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, front-loaded with the action and immediately qualified by the affected resources. No filler.

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

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

An output schema exists and there are no parameters, so the description only needs to convey the effect, which it does. Only the no-active-session edge case is missing.

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

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

The tool takes zero parameters, so there is nothing to disambiguate; the baseline of 4 applies. Nothing in the description contradicts the empty 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 ('Stop') and resource ('the live session') and the parenthetical enumerates exactly what is torn down (camera, microphone, streams). An agent can immediately tell this is the teardown counterpart to live_start 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: the sibling set contains live_start, so calling live_stop after live_start is obvious. The description gives no explicit when-to-use or precondition (e.g., whether an active session must exist, or what happens if none does).

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

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

With no annotations, the description carries the full burden and does not disclose whether adding triggers replaces or appends to the existing set, whether removal of a nonexistent trigger errors, or whether changes persist after `live_stop`. "Change" signals mutation but the mechanics and reversibility are left entirely implicit.

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

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

A single tight sentence with no filler, and the resource is front-loaded after the verb. It is efficient but so short that it omits necessary operational detail rather than being optimally dense.

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, but for a mutation tool with zero annotation coverage and 0% parameter documentation, the description leaves the add/remove semantics and session prerequisite unaddressed. It is not complete enough for an agent to invoke this 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?

Schema description coverage is 0% — `add` and `remove` are bare arrays of strings with no descriptions. The description never mentions these two parameters, so it fails to compensate: an agent cannot tell whether `add` is additive or a full replacement, or how strings are matched for `remove`.

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 ("Change") and resource ("visual triggers") and adds a clarifying parenthetical that these are descriptions of things to watch for. It scopes the change to the running session, which implicitly separates it from a persistent `watch` tool, though it never names a sibling explicitly.

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

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

There is no guidance on when to use this versus `watch`, `list_watches`, or `live_start`. The phrase "running session" hints that a live session must already exist, but no prerequisite or exclusion is stated outright.

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

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

No annotations are provided, so the description carries the full behavioral burden. 'Show' implies a read operation and the artefact list adds useful context, but the description does not state permissions, side effects, error behavior, or result format.

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 an efficient inline list. It wastes little space, though the dense enumeration could be slightly clearer for an agent unfamiliar with the domain.

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 annotations, no output schema, and 0% schema description coverage, the description should do more. It explains the 'what' values but does not explain watch_id semantics, return behavior, or invocation context needed for a fully self-contained tool definition.

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 usefully defines the accepted forms for 'what' (sheet:N, timeline:N, view:N, shot:N, page:N, colour), but it leaves 'watch_id' and the meaning of 'N' unexplained.

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 clear verb and resource: 'Show an artefact of a watch.' It further enumerates the artefact types (sheet, timeline, view, shot, page, colour), so the agent can understand the operation. It does not explicitly differentiate 'look' from similar siblings such as frame, image, images, or zoom.

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 lists valid artefact types but provides no when-to-use guidance, no exclusions, and no routing to alternatives. With many visually overlapping siblings, an agent receives no help deciding when 'look' is the right tool versus image, frame, or zoom.

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 burden well: it explains what hitches mean, that effective fps is per second, that flashes above 3/sec are flagged for photosensitivity, and that the result is a summary plus chart. It only leaves out side effects such as whether an analysis artifact is persisted or what permissions/limits apply.

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 front-loaded with the purpose and then packs in the relevant measurement details in a single dense paragraph. Every clause relates to capability, parameter usage, or return value, though the density makes it slightly harder to scan than a bulleted structure.

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

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

There is no output schema, so the description must explain returns; it does so minimally with 'Returns a summary plus a chart.' For a four-parameter analysis tool with no annotations, the missing definitions for start/end and the sparse return-value detail 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 must compensate. It adds useful meaning for source (file, URL, or watch id) and fov_deg (horizontal headset field of view for deg/s comfort analysis), but gives no explanation for start or end, leaving half the parameters 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 clearly defines a specific analysis resource: QA of game/XR/app recordings across frame pacing, stereo, comfort, and flash/photosensitivity metrics. It is distinguishable from the sibling tools by its diagnostic focus, though it never explicitly contrasts itself with tools like frame or live_watch_for.

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?

It implies the tool is for analyzing recordings from a file, URL, or watch id, but does not state when to choose this over alternatives such as frame or live_snapshot. Usage is inferable from the metric list but not explicitly routed.

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

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

With no annotations, the description carries the full burden and does well: it discloses scope differences (text hits cover every watch, visual moments only the selected watch_id), that results include a contact sheet of best frames/album images, the score thresholds (strong >= 0.5, possible >= 0.05), and the first-visual-search indexing latency. It stops short of stating read-only semantics explicitly, result limits, or error behavior.

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

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

Four dense sentences, each carrying distinct information (capabilities, coverage, scoring, indexing cost), with the core purpose front-loaded. No filler or restatement of the tool name.

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 3-parameter, no-annotation, no-output-schema search tool, the description covers what is indexed, which watches are covered, what comes back (contact sheet), how to interpret scores, and the indexing delay. The main omission is how the 'visual' flag behaves and any notion of result count or pagination.

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 adds real meaning for watch_id ('default: the most recent watch', beyond the schema's bare null default) and richly characterizes the query string. But the 'visual' boolean is never named or explained — an agent must infer that visual=false yields text-only results across all watches.

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 ('Find moments') and enumerates all three search modalities with concrete query examples ('a red car at night', 'a pie chart', 'someone hugging'). An agent can immediately tell this is a multimodal content search rather than a frame retrieval or navigation tool like frame/zoom/look.

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?

Provides useful in-tool context about what kinds of queries work, that all-weak visual scores mean the thing is probably absent, and that negation is unsupported. However, it never routes the agent against the 15 siblings (frame, look, zoom, images, list_watches) — there is no statement of when to prefer this tool over browsing a specific frame or listing watches.

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 at all, the description carries the full burden and does well: it discloses the return value (INDEX.md plus first overview contact sheet), performance cost (~1-2 s per minute on first run), and auth behavior for gated URLs. The 'force' behavior and whether results are cached on subsequent runs are left unexplained.

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?

Purpose is front-loaded in the first sentence and the remaining lines each add a distinct fact (mode, windowing, cookies, return value, cost). It is dense but not padded; the middle sentence is a long run-on that slightly hurts scannability.

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?

There is no output schema and no annotations, so the description correctly compensates by naming the returned artifacts and noting the initial processing time. The unexplained 'force' flag is the one remaining gap for an agent deciding how to call it.

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, and it does for 5 of 6 parameters: mode values (auto | film | screen with screen explained), start/end accepted formats plus the key semantic that 'times stay in full-video time', and cookies_from_browser values/conditions. Only 'force' receives no explanation.

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 first sentence gives a specific verb and resource ('Analyse a local video file or URL') and enumerates supported platforms, which makes the opaque name 'watch' unambiguous. It does not explicitly distinguish itself from siblings like frame, look, or live_watch_for, 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?

Offers concrete when-to-use guidance: start/end windowing is recommended 'for long videos when the question is about one stretch', and cookies_from_browser is restricted to login-gated URLs 'only with the user's OK'. No sibling alternatives are named for choosing between watch and frame/zoom/look, so it is clear context without explicit routing.

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 burden of behavioral disclosure. It usefully states a hard limit ('up to 30 frames') and timestamp format, but does not explicitly confirm read-only behavior, permissions, or what happens with invalid ranges.

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 tight sentence with no filler. Information is front-loaded around output shape and scope, and every phrase adds useful meaning.

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

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

For a four-parameter tool with no annotations, no output schema, and 0% schema description coverage, the description is too sparse. It omits the meaning of `watch_id`, the role of `n`, and enough return-value detail to compensate for the missing 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?

Schema description coverage is 0%, so the description must compensate for four undocumented parameters. It explains the `start` and `end` time formats and implies a maximum frame count, but never explains `watch_id` or clearly defines `n` as the requested number of frames.

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 the resource and scope: a dense timestamped grid of frames between two timestamps, capped at 30 frames. It lacks an explicit action verb such as 'returns' or 'retrieves', but an agent can still infer the tool's function. It does not explicitly differentiate itself from the sibling `frame` tool or other frame-related siblings.

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 gives no guidance on when to use this tool versus alternatives such as `frame`, `images`, or `look`. The interval and frame cap imply it is for multi-frame sampling, but there are no explicit when-to-use or when-not-to-use conditions.

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