StreamClipping AI

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

Beyond the destructiveHint annotation, the description discloses important conditional behavior: failed or already-cancelled posts are permanently deleted, and the response's action field reports what occurred. This adds substantial context about outcome and idempotency that annotations alone do not provide.

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?

Three sentences, front-loaded with the core action and immediately followed by edge-case behavior and response disclosure. Every sentence adds useful information with no waste.

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 low-complexity, single-parameter tool with rich annotations and an output schema, the description covers the essential behavioral nuance (live vs. not live, conditional deletion, response field) without needing to restate return values. It is complete for correct 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 coverage is 100% for the single scheduledPostId parameter, so the schema already documents its meaning and expected status. The description adds no syntax, format, or additional semantics beyond what the schema provides; baseline 3 is appropriate.

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

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

The description gives a specific verb and resource ("Cancels a post") and adds meaningful scope ("that has not gone out yet" / "no effect on a post that is already live"). It does not explicitly name or route against any sibling tool, so it is clear but lacks sibling differentiation.

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 clearly states when the tool applies (scheduled, not yet live) and when it has no effect (already live). It does not name alternative tools or explain how to choose another sibling, so it falls short of the top 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?

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered structurally. The description adds concrete consequence detail beyond the annotations: the deletion is permanent and the video file is erased. It omits auth requirements and failure behavior, so it falls short of a 5.

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

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

Two short sentences with zero filler; the permanence consequence and the confirmation requirement are both front-loaded. Every sentence carries information an agent needs.

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

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

An output schema exists, so return values need not be explained, and annotations cover destructiveness. The description supplies the remaining critical facts (irreversibility, confirmation requirement) for a destructive two-parameter tool, though it says nothing about what happens on a false confirm or missing clipId.

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 50%: 'confirm' is documented in the schema but 'clipId' has no description anywhere. The description reinforces that confirmation is explicit and required, adding minor value, but it does not compensate for the undocumented clipId parameter (format, source of the id). Baseline 3 is appropriate given partial coverage.

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 ('deletes a clip') plus scope beyond the name ('and its video file'), which lets an agent distinguish it from get_clip, list_clips, and update_clip. It does not explicitly name a sibling, but the destructive verb makes the boundary obvious without opening schemas.

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 states a prerequisite ('Requires an explicit confirmation argument'), which is genuine usage guidance. However, it gives no when-to-use/when-not context versus siblings like update_clip or cancel_scheduled_post, and does not explain when deletion is appropriate. Guidance is implied by the destructive verb 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?

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the mutation profile is covered. The description adds that detected moments are approved as a side effect, but says nothing about rendering being long-running/asynchronous or how to track progress. Adequate but thin beyond the annotations.

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 sentence, zero waste, with the action and the gating status front-loaded. Nothing to trim and nothing buried.

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-value explanation is unnecessary, and the precondition is covered. However, for a render-triggering job the description omits whether rendering is asynchronous and how the agent should follow up, which is material given the presence of get_project and retry_project siblings.

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

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

There is a single parameter with 100% schema description coverage; the schema already explains that projectId must reference an AWAITING_REVIEW project. The description merely restates that constraint, adding no new meaning. Baseline 3 applies when the schema carries the parameter load.

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 specific verbs and resource: approves detected moments and starts rendering videos for a project. The AWAITING_REVIEW precondition distinguishes it from siblings like start_clipping and retry_project, though it never names an alternative 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?

Gives clear preconditions - the project must be in AWAITING_REVIEW status - which tells the agent when this tool applies. It does not state what to do instead for projects in other statuses or how this relates to start_clipping.

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 establish a safe, closed-world read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lowered, and the description still adds real behavior: imports fail when minutes run short, and the trial quota is one hour of video per day refilled at midnight local time surfaced in the trialDaily field. That is meaningful operational context beyond the structured data.

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?

Three sentences, front-loaded with the returned field list and then the quota mechanics. Every sentence carries information; nothing is padding, though the phrasing is slightly list-like rather than tightly organized around a single intent.

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 is not obliged to explain return values, yet it usefully characterizes them plus the quota-refill rule and the consequence of exhaustion. For a no-parameter, read-only status tool this is essentially complete; only the relationship to get_analytics is unaddressed.

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 and schema coverage is moot. The description correctly spends no space on 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 names the resource (the account) and enumerates exactly what is returned: plan, processing minutes, magic clipping quota, connected social accounts. That is far more specific than the title. It stops short of distinguishing itself from the adjacent sibling get_analytics, which an agent could plausibly confuse with quota/usage 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?

Usage is only implied: the note that 'an import fails when minutes run short' hints that this tool should be consulted before/after import_vod, but it never states when to call it or how it differs from get_analytics. No explicit when-to-use or when-not-to-use guidance is 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?

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds a genuinely useful behavioral constraint beyond that: results only cover posts published through StreamClipping AI, which tells the agent why coverage may be incomplete. Return format and aggregation semantics are left to the output schema.

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

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

Two short sentences, zero filler. The positive statement of what is returned is front-loaded and the coverage caveat follows immediately, so nothing has to be scanned for.

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, return values need no explanation, and annotations carry the safety profile. The description supplies the one thing structured fields can't: the StreamClipping-AI-only data scope. Only the absence of guidance on the 'per platform' breakdown versus parameters is a residual 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?

Schema description coverage is 100%, with creator and periodDays both fully documented in the schema, so the baseline is 3. The description's 'over a period, per platform' loosely gestures at periodDays but says nothing about creator scoping or the 'default' sentinel, adding little 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 names the concrete outputs (views, likes, top posts), the aggregation window and the breakdown dimension (per platform), so an agent can tell it is the reporting tool rather than a listing or mutation tool. It is clear but never states a verb or explicitly contrasts itself with siblings such as get_account or list_clips.

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: reading performance metrics. There is no statement of when to reach for this versus the sibling listing tools, nor any prerequisite (e.g., needing published posts to exist). The scope caveat 'only covers posts published from StreamClipping AI' hints at when results will be empty but is framed as data scope, not usage 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds the set of metadata fields, but this largely duplicates the available output schema and does not disclose permissions, error behavior, or how the clip is identified.

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

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

A single front-loaded sentence that lists the metadata categories without introductory fluff. It is appropriately sized, though the field list is somewhat redundant given an output schema exists.

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 lookup tool with one required parameter and an output schema, the description covers returned fields but leaves the parameter and call context unaddressed. It is adequate at a high level but missing the practical details an agent needs to invoke 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?

Schema description coverage is 0% for the single required clipId parameter, and the description never mentions clipId or explains its expected format/source. The name is intuitive, but the description contributes no semantics beyond the raw 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 the resource (clip metadata) and enumerates the fields returned, making the tool's output clear. However, it omits an explicit retrieving verb and does not differentiate from siblings like list_clips or get_project, so it is clear but not fully distinguishing.

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

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

No when-to-use guidance, no mention of alternatives such as list_clips, and no prerequisites (e.g., needing a clipId from list_clips). The agent receives no routing information.

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, destructiveHint=false and a closed-world scope, so the safety profile is covered. The description adds real value on top: it enumerates the observable pipeline state, exposes error reporting, and hints at polling cadence, plus an explicit negative scope ('Does not return the transcript') that prevents a wrong-expectation call.

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 sentences, zero filler: the first front-loads what the agent gets back, the second closes the one non-obvious gap (no transcript). Nothing is repeated from the annotations or schema.

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-value exposition is not required, and the description still gives an accurate summary of the payload plus the polling cue. Only minor gaps remain (auth requirements, error/failure semantics when the project does not exist or is not found).

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?

One parameter with 100% schema coverage; the schema already documents projectId as the project identifier. The description adds no syntax, format, or sourcing guidance for the ID, so the baseline 3 applies.

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+resource ('Detailed status of a project') and enumerates the returned contents (pipeline steps, error, clips, next action, polling delay), which lets an agent separate it from list_projects or get_clip. It stops short of naming any sibling explicitly, so differentiation is inferred rather than stated.

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

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

Implied usage only: mention of 'next expected action' and a 'suggested polling delay' signals this is the status-polling call after starting a project, but the description never says when to prefer it over list_projects or retry_project, nor states prerequisites such as a project already existing.

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 the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the bar is lower. The description adds real behavioral context beyond the annotations: it clarifies that import is a non-clipping state transition and exposes the AWAITING_CROP milestone. It does not cover auth requirements or behavior on private/ongoing streams, but the schema's url description handles the latter.

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 sentences, zero waste. The core action is front-loaded and the workflow constraint follows immediately; nothing is padded.

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

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

With an output schema present, return values need not be explained, and the annotations plus 100% schema coverage carry safety and parameter detail. The description supplies the one thing structured fields don't: where this sits in the import→start_clipping pipeline. Slight gap on failure modes keeps it from a 5.

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 four parameters (url, title, creator, language) are already fully documented in the schema. The description adds no syntax or format detail beyond it, so the baseline of 3 is appropriate.

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

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

States a specific verb and resource: 'Creates a project from a ... VOD (stream replay) link,' and enumerates the supported platforms (Twitch, YouTube, Kick, CHZZK). It also distinguishes itself from the workflow sibling start_clipping, so an agent can place it 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?

Gives clear context and the expected next step: importing is not clipping, and start_clipping follows once the project reaches AWAITING_CROP. It stops short of naming when NOT to use it (e.g., re-importing an existing VOD via list_channel_vods), but the workflow routing is explicit.

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=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the account-connection prerequisite and hints at the returned link, but it is slightly redundant with the platform param description and says nothing about how 'recent' is determined or about result limits/pagination.

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 tight two-clause sentence with the resource and the actionable purpose front-loaded; every phrase carries information. Nothing is wasted, though it could be marginally clearer about ordering/limit in the same 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 an output schema present, the description need not explain return values, and it correctly supplies the prerequisite and downstream-use hint. The main gap is silence on the limit parameter and recency semantics, which an agent calling this list tool would benefit from knowing.

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 only 50%: platform is documented in the schema, while limit exists only with structural constraints (default 10, max 50). The description does not mention limit or what 'recent' ordering means, so it fails to compensate for the uncovered parameter, leaving it at minimum-viable.

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 resource (recent VODs / stream replays) for a defined scope (the connected Twitch or YouTube channel), and clarifies the payload's purpose by naming the downstream tool import_vod. It is clear enough to separate from list_clips, though it does not explicitly contrast with that sibling.

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 clear context of use (fetching VODs to pass their link to import_vod) and an explicit prerequisite (the matching account must be connected). It stops short of stating when not to use it or naming a competing sibling to avoid.

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=true, destructiveHint=false and openWorldHint=false, covering the safety profile. The description usefully adds the default sort (viral potential) and the source of titles/hooks, but says nothing about pagination/cursor limits or result volume beyond what the schema provides.

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 sentences, front-loaded with scope and default ordering, with no filler. The second sentence about titles/hooks earns its place by explaining where those fields originate.

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

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

An output schema exists so return values need not be described, and annotations cover the safety profile. Scope and default ordering are stated; the definition is adequate for a low-risk, zero-required-parameter listing 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 description coverage is high (83%) with self-documenting descriptions for cursor, sortBy, status, creator and projectId, so the structured data carries the load. The description's mention of 'account or of one project' and default sort largely restates the schema rather than adding syntax or edge-case meaning.

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 ('Clips of the account or of one project') plus the default sort behavior, making the scope clear. It does not explicitly distinguish itself from the singular sibling get_clip, relying on the plural to imply listing.

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 listing nature of the tool; there is no explicit when-to-use guidance or reference to alternatives such as get_clip for a single clip or list_projects for project scoping. An agent can infer its role but is given no routing rules.

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 a safe, read-only, closed-world operation, so the bar is lower. The description still adds value by disclosing the default ordering (newest first) and what each returned project carries (status and next expected action), which goes beyond the annotation set. It stops short of mentioning pagination or page-size 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?

A single sentence that front-loads the resource, then scope, then ordering, then returned fields. No filler 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?

An output schema exists, so return-value detail is not required, and the description still previews the notable fields. For a simple, low-risk list tool with fully documented parameters and annotations, this is nearly complete; only pagination/refresh semantics are unaddressed.

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 the schema already documents limit, cursor, and creator thoroughly. The description adds only the 'newest first' ordering, which largely duplicates the limit parameter's own description. Baseline 3 is appropriate.

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

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

States a clear verb+resource ('Video projects of the account') plus scope and ordering ('newest first') and the fields returned ('status and the next expected action'). It is easily distinguished from get_project or list_clips by name, though it never explicitly contrasts itself with 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?

Usage is implied by the name and the scoping to 'the account', but there is no explicit when-to-use guidance, no mention of when to prefer get_project for a single project, and no stated 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?

Annotations already declare a safe, read-only, non-destructive, closed-world operation. The description adds that returned items include a public link and view count, which is mild context, but it says nothing about pagination, ordering, or the 50-item cap behavior that annotations don't cover.

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 filler, which is efficient, but it is a bare noun phrase that leads with enumeration rather than stating the action and scope up front.

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

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

An output schema exists so return values need not be spelled out, but the description leaves dangling basics: which organization/creator scope is default, how limit behaves, and how this differs from the other list_* tools. For a zero-required-parameter listing tool this is thin.

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 50%: the creator parameter is fully documented in the schema, but limit has no description and the tool description compensates for neither. It adds no syntax, default, or scoping detail beyond what the schema already provides.

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 (posts) and enumerates the statuses covered (scheduled, in-progress, published, failed), plus the payload (public link, view count). However, it has no verb and never distinguishes itself from sibling list tools like list_clips or list_projects, so an agent must infer that this is the post-listing endpoint.

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 mention of how this relates to cancel_scheduled_post, schedule_post, or the other list_* siblings, and no note on default scoping (limit defaults to 20, creator omitted covers all creators). The agent gets no routing help.

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=true, destructiveHint=false and a closed-world scope, so safety is covered. The description adds useful content context (status plus publish capability per account), but says nothing about freshness, ordering, or whether disconnected accounts appear; with an output schema present, deeper return detail is not required.

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 no filler, front-loading the resource and then the payload it returns. It is appropriately sized for a zero-parameter list tool.

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

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

For a read-only, parameterless lister with an output schema and clear annotations, the description supplies enough to call it correctly. The only minor gap is the absence of any statement about filtering or ordering of the returned accounts.

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 is 4. There is nothing for the description to disambiguate on the input side.

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 ('Social accounts connected to the StreamClipping AI account') and scopes the content to status and publishability. It is clearly distinguishable from action-oriented siblings like schedule_post or delete_clip, though it never explicitly contrasts itself with them.

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 content description: an agent can infer this is the tool to call to discover which accounts exist and which can be published to. There is no explicit when-to-use statement, no prerequisite/permission note, and no named 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 declare idempotentHint=true, destructiveHint=false and readOnlyHint=false, so the mutation profile is largely handled structurally. The description adds real value beyond that by disclosing resumption semantics: it continues from the last valid step rather than re-running from scratch and is non-destructive. It omits what happens if the project is not in FAILED status or whether the retry is long-running.

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 with no filler, front-loading the action and the state constraint. Every clause earns its place.

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

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

For a one-parameter action whose safety profile is covered by annotations and whose return values are covered by an output schema, the description is essentially sufficient. Minor gaps: failure behavior on non-FAILED projects and whether the operation is asynchronous.

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?

Only one parameter and schema description coverage is 100%; the schema already states 'Project in FAILED status.' The description reiterates the same constraint, adding no format, ID-source, or lookup guidance beyond it. Baseline 3 applies when the schema carries the parameters.

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 (resumes) plus the resource (project) and its applicable state (FAILED status). The clause 'from the last valid step, without starting over' makes it distinguishable from a fresh-start tool like start_clipping or generate_clips, though no sibling is 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 precondition is clear: the project must be in FAILED status, which is the when-to-use condition. It does not state what to do instead when the project is not FAILED, so the alternatives side is left to inference.

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 non-read-only, open-world, non-idempotent behavior; the description adds timing semantics ('without a date, the post goes out within a minute'), a mandatory confirmation gate, and plan-based authorization limits, none of which the annotations express. Irreversibility is stated but largely duplicated from the confirm parameter's schema text.

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 tight sentences with no filler, leading with what the tool does and the platforms it targets. The closing TikTok sentence is slightly tangential but still earns its place as an explicit exclusion.

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, return values need no explanation, and the annotations cover the safety profile. The description completes the picture with plan gating, confirmation requirement, and scheduling-vs-immediate behavior; only the prerequisite that the clip be READY is left to the 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 coverage is 100%, so all six parameters are already documented, including scheduledAt's ISO 8601 format and confirm's boolean requirement. The description only reinforces the omitted-date behavior, which the schema already states, so it adds little beyond the structured fields.

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

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

States a specific verb (schedules) plus resource (a clip) and the exact destinations (YouTube Shorts, Instagram Reels, X), which cleanly separates it from siblings like list_scheduled_posts and cancel_scheduled_post. An agent can identify the operation and its scope 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?

Gives concrete usage conditions: X requires a paid Pro/Elite plan (explicitly ruling out Free, Creator, trial, gifted), omitting a date means near-immediate publication, and TikTok is handled elsewhere ('published from the app'). It does not name sibling alternatives directly, but the platform exclusions and plan gating provide real routing 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?

Annotations only flag it as a non-idempotent, non-destructive write. The description adds material behavior beyond that: it consumes processing minutes proportional to processed duration and one magic credit when automatic mode is on. It still does not say whether the call blocks or runs asynchronously, nor what happens to credits 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?

Two sentences, zero filler, and the precondition plus cost model are front-loaded rather than buried.

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, return values need no explanation, and the description covers precondition, cost, and the automatic-mode branch. It is nearly complete for a 3-parameter start action, missing only the async/blocking nature of the operation.

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 the schema already documents projectId, magic and startAtSec in detail; baseline is 3. The description only restates the magic/automatic-mode credit link, adding a little cost context but no syntax or format meaning 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?

Specific verb plus resource: starts transcription and moment detection on a project, with the required AWAITING_CROP precondition named. An agent can distinguish it from delete_clip/update_clip/list_projects, though it does not explicitly differentiate from the nearby generate_clips sibling.

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 AWAITING_CROP precondition gives implied usage context, but there is no explicit guidance on when to choose this over generate_clips or retry_project, and no statement of what to do if the project is not in that status.

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

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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description corroborates this with 'overwrites ... with the values given'. More importantly it discloses non-obvious behavior annotations cannot: editing does not re-render the video, so a hook change only takes effect in the file after a new render. That is real added value beyond structured fields.

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 tight sentences, zero filler, and the operative fact (what gets overwritten) is front-loaded before the caveat about rendering. Every clause earns its place.

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

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

An output schema exists, so return values need not be explained, and annotations carry the safety profile. The description covers the main gotcha (no re-render), but omits what happens to fields not supplied and any permission/lock requirements for editing a clip.

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 80%, so the schema already documents most parameters (title, hashtags 'without the # sign', hookText, description). The description only restates those field names as a group and adds the render caveat for the hook; it does not clarify whether omitted fields are left untouched or cleared. Baseline 3 is appropriate.

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

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

The description names a specific verb (overwrites) and enumerates the exact editable fields (title, description, hashtags, hook) on a clip, so the agent can identify it as a metadata-mutation tool. It stops short of explicitly contrasting with siblings such as get_clip or delete_clip, but the resource and operation are unambiguous.

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 by the mutating verbs and the field list, but the description offers no explicit when-to-use guidance, no prerequisites (e.g. clip must already exist / be rendered), and no mention of alternatives if any exist. Nothing is misleading, but an agent must infer the calling context.

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