Tegas

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

The readOnlyHint and destructiveHint annotations already indicate a safe read operation. The description adds value by explaining plan.gating consequences for POST tools and the insufficient_tokens failure mode, so the agent knows why this read matters beyond its own result.

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

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

The description is compact and front-loaded, opening with 'Free. Account overview' before moving to concrete usage rules. Every sentence adds operational value, including price computation and user-facing error handling, 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 zero-parameter read-only account tool with an output schema, the description covers everything an agent needs: what the tool returns, when to call it, how to compute cost, and how to react to the two likely failure conditions. Nothing essential 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 has zero parameters and schema coverage is 100%, so there is no parameter ambiguity to resolve. The description references meaningful output fields like plan.active and tokens_per_second, which indirectly clarifies the data an agent should read from the result.

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 tool as an account/pricing overview: token balance, active plan, rate limits, and per-quality token prices. It also distinguishes itself from the video-generation sibling tools by being the read-only account-status tool to call first.

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 explicit when-to-use guidance: call this first to check balance, and before starting a video to compute price as tokens_per_second[quality] * duration_sec. It also provides concrete fallback behavior for no_active_plan and insufficient_tokens, which fully instructs the agent on when and how to respond.

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 say the tool is not read-only and not destructive, but the description adds substantial behavioral detail: paid operation, dry-run behavior with confirm=false, side effects of attaching sheets to the scenario, idempotency_key retry semantics, and specific error handling for insufficient_tokens and no_active_plan. No contradiction with 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?

The description is dense but front-loaded with 'PAID' so the cost-sensitive nature is the first word, and every sentence carries operative guidance: cost formula, confirmation flow, attachment behavior, retry key, and error handling. There is no filler or repetition.

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

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

The description fully compensates for the sparse schema by covering pricing, the mandatory confirmation workflow, integration with tegas_start_video, idempotent retry behavior, and the two expected error states. Since an output schema exists, further return-value documentation is unnecessary.

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?

With 0% schema description coverage, the prose explains all parameters: items are brief indexes from tegas_find_heroes, price_each_tokens should come from the prior call, confirm controls whether anything is drawn, scenario_id links to the scenario, and idempotency_key is for retries. Minor ambiguity remains: the description says 'chosen by `index`' while the schema parameter is the array `items`.

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 ('Draw hero sheets') and ties it to a concrete input source (brief items from tegas_find_heroes, up to 3). This clearly distinguishes it from sibling tools by positioning it as the paid drawing step that feeds tegas_start_video.

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?

Spells out a complete invocation protocol: call first with confirm=false, show the price, ask for consent, then call with confirm=true after explicit approval. It also names the sibling functions it coordinates with and explains when not to proceed (before confirmation), so usage is fully 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 destructiveHint=true and readOnlyHint=false, and the description reinforces and expands on this: it explicitly states the call REPLACES the whole video end to end, takes several minutes, and is not a quick patch. It also discloses failure modes (422 validation_error for illegal combinations, 409 video_busy) and notes that the operation is free. This goes well beyond what annotations alone 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?

The description is long but every section earns its place: the most critical warning (full rebuild, not a quick patch) is front-loaded, parameter groups are organized into scannable bullets, and constraints are placed next to the parameters they affect. There is no redundant restatement of the schema or filler content.

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

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

For a 7-parameter tool with an empty schema-coverage rating and complex interaction rules, the description covers everything needed: return values (video_id, status, edits_accepted), error handling (409, 422), polling guidance, and the destructive cost of the operation. An agent can confidently decide when and how to invoke the tool without additional external knowledge.

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?

With 0% schema description coverage and open object types, the description carries the full burden of parameter documentation. It details each parameter group with field lists, types, omission behavior, and constraints—e.g., scenes entries need at least one of three fields, volumes range 0..100, and watermark must be a standalone change. This is exemplary compensation for an uninformative 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 states a specific action ('Edit a finished video in place and rebuild it') and clearly scopes the resource: a finished video. It differentiates itself from creation and status tools through the 'finished video'/rebuild framing, but it doesn't explicitly name an alternative like tegas_start_video. This is clear enough to avoid confusion, though not maximally explicit on 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?

The description gives explicit operational guidance: tell the user before calling, poll with tegas_wait_video or tegas_video_status, and do not call again for the same video until the rebuild finishes. It also provides precise conditional rules, such as watermark must be the only change and subtitles cannot be disabled and restyled in the same call. It doesn't contrast itself with alternatives for editing vs. creating, but within its own domain the usage guidance is thorough.

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 say readOnlyHint=false and destructiveHint=false, which is minimal. The description adds meaningful behavioral context: it's free (requires active plan), returns up to 3 items with specific fields, includes price_each_tokens, and clarifies that drawing is a separate paid step. This goes 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?

The description is compact and information-dense. It front-loads the cost/free status, then the output, then the style parameter, then the sibling relationship. Every sentence earns its place.

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

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

Given the output schema exists, the description doesn't need to explain return values in detail, but it does summarize them. It covers cost, style options, and the separate drawing step. Minor gap: it doesn't explain what 'hero product' means or how scenario_id is obtained, but the sibling list and output schema fill some context.

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 explains the style parameter by listing the allowed values and noting 'omit to follow the scenario', and it explains scenario_id implicitly as the scenario context. It doesn't detail scenario_id format, but the schema already names it and the description's style guidance adds real value.

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

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

The description clearly states the tool finds recurring heroes for a scenario, with a specific verb ('find'), resource ('recurring characters and hero product'), and output details. It distinguishes itself from the sibling tegas_draw_heroes by noting drawing is a separate paid step.

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

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

The description provides clear context: it's free but requires an active plan, and it explicitly says drawing is a separate step via tegas_draw_heroes. It doesn't explicitly state when not to use it, but the alternative is named and the relationship is clear.

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 mark this as read-only and non-destructive. The description adds useful behavioral context beyond annotations: the operation is free, returns videos newest-first, enforces a limit of 1..100, and includes specific fields like status and file_url.

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 extremely concise, with no filler. It front-loads the most valuable distinguishing detail ('Free') and packs ordering, range, and result fields into one efficient 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 simple single-parameter list tool, the description is complete. Output schema covers the return shape, annotations cover safety, and the description explains the ordering, limit range, and included fields. No critical calling information 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?

Schema description coverage is 0%, so the description must compensate for the lone `limit` parameter. It does so by clarifying the valid range (1..100), which is absent from the schema, and by implying that limit controls how many videos are returned.

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 action and resource: listing the user's most recent videos. It adds specifics—newest first, limit range, and returned fields—that distinguish it from singular status-checking tools like tegas_video_status.

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

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

The description implies when to use the tool: when you need a user's recent videos and their metadata. However, it does not explicitly mention alternatives or state when not to use it, such as checking a single video's status with tegas_video_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?

The description goes far beyond the basic readOnlyHint/destructiveHint annotations: it discloses that the operation is paid, how cost is computed, that confirm=false does not start anything, that confirm=true starts a render, that idempotency_key protects against double charges, and what each error means. This is exactly the contextual behavior an agent needs before invoking a paid, state-changing tool.

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

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

Although the description is long, it is dense and front-loaded: the paid nature, the exclusive input requirement, cost formula, confirmation flow, retry rule, follow-up call, and parameter meanings are all packed into a compact structure. Every sentence contributes operational value, and none restate the schema in a redundant way.

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 both branches of behavior (confirm=false and confirm=true), the returned fields (needs_confirmation, price, balance, video_id, status queued, idempotency_key), failure/retry behavior, and error-specific user actions. It also links to related tools (tegas_account, tegas_voices, tegas_write_scenario, tegas_wait_video) making it fully actionable.

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?

Input schema coverage is 0%, yet the description compensates for every parameter: scenario_id/scenario_text exclusivity, quality enum values, voice coming from tegas_voices, defaults for music/subtitles/watermark, the meaning of confirm, idempotency_key retry semantics, and reference_urls. It adds essential meaning beyond the schema field names and defaults.

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

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

The description opens with 'PAID. Start rendering a video' and immediately clarifies the two possible sources: 'a Tessa scenario (scenario_id) or your own scenario_text - exactly one of them.' It uses a specific verb, names the resource, and distinguishes the operation from sibling tools like edit or wait by describing the render-start action.

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 explicit workflow guidance: pass duration_sec returned by tegas_write_scenario, call again with confirm=true only after explicit consent, retry with the same idempotency_key on failure, and 'Then call tegas_wait_video.' It also provides error-specific actions for insufficient_tokens, no_active_plan, and rate_limited, which gives the agent clear when-to and when-not-to territory.

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?

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses all relevant behavior: it requires an active plan, returns a stored URL with an expiry, enforces a 25MB limit and specific formats, and details all possible error codes (validation_error reasons, file_not_readable, local_files_disabled). It also explains that file_path only works when the server enables it, providing complete transparency about environmental 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?

Although the description is long, it is meticulously structured with the core purpose stated first, followed by parameter details, return values, and error handling. Every sentence adds unique value—format limits, error codes, and integration guidance are all essential. There is no redundancy or fluff; the density is justified given the complexity of the tool.

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

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

Given the tool's complexity (error handling, multiple input modes, external integration), the description is complete. It covers inputs, outputs (music_id, url, label, expires_at), error handling, prerequisites (active plan), and downstream usage. It also accounts for the readOnlyHint=false annotation by explicitly labeling the action as an upload. Nothing an agent needs to invoke correctly 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 schema provides only property names and types with zero descriptions (0% coverage). The description compensates fully: it explains audio_base64 accepts both raw base64 and data:audio/mpeg;base64 URLs, details the file_path limitation to the server's filesystem, and specifies label is truncated to 120 characters. This added semantics is critical for correct usage and is perfectly delivered.

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 precise purpose: upload one music track and return a URL for reuse in tegas_edit_video's music.url. It names the verb (upload), the resource (music track), and the output (url), leaving no ambiguity about what the tool does. It also implicitly differentiates from siblings by focusing solely on music upload while other tools handle videos or scenarios.

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

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

The description provides explicit usage guidance: it explains the two input methods (audio_base64 and file_path), when each is appropriate (remote vs local/self-hosted), and what to do if the server disables local files (fallback to audio_base64). It also clarifies format and size limits, and instructs the agent on how to use the returned URL in tegas_edit_video, including setting music.enabled. This is comprehensive and leaves no decision 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 only flag readOnlyHint=false and destructiveHint=false; the description goes far beyond that. It discloses validation-before-upload behavior, a complete list of validation_error codes and their meanings, the file_not_readable and local_files_disabled errors, return contents, TTL expiry, and the plan requirement (no_active_plan). No contradiction with 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?

The description is long but every sentence delivers actionable detail. It opens with the core function and return value, then explains each parameter, lists error codes in a structured way, and closes with integration and error handling. No filler or repetition; the density is justified by the tool's many edge cases.

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 modest 3-parameter tool, the description covers all necessary usage details: parameter selection, size/format constraints, validation errors, return values, expiry, integration with sibling tools, and plan errors. An output schema exists but the description already explains the return fields, so an agent has everything needed to invoke the tool correctly without external resources.

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 carries the full burden. It explains label as an optional short note limited to 120 characters, file_path as a server-side path only for local runs, and image_base64 as base64 bytes or a data URL accepted without needing public access. It also links error codes to specific parameter failures (both/neither, bad_base64, etc.), adding semantic meaning beyond the schema's bare property names.

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 ('Upload one reference image and get a reference_id to reuse') and clearly identifies the resource (reference image) and the outputs. It differentiates from siblings by mentioning how the result feeds into tegas_write_scenario or tegas_start_video, and the context of reference images for products, characters, brands is explicit.

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 explicit when-to-use guidance for the two source parameters: image_base64 for remote agents (image never needs to be public) and file_path only for local/self-hosted runs with server enablement, including the fallback if local files are disabled. It also explains when to re-upload (TTL expiry) and how to pass the returned reference_id to other tools.

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

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

Annotations declare readOnlyHint=true and destructiveHint=false, which the description aligns with. Beyond that, the description adds useful behavioral context: it states it is 'Free', that tokens are refunded on failure, and describes the output fields (file_url when completed, error when failed). This goes beyond the annotations and helps the agent understand side effects and failure 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?

The description is one sentence, front-loaded with 'Free' and 'Status', and packs all essential information without fluff. Every phrase adds value: statuses, progress range, success/failure fields, and refund policy.

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 the output fields (status, progress, file_url, error) and the refund behavior, which is sufficient for a read-only status check. An output schema exists, so return format is also available. The only missing context is how to obtain video_id, but that is likely covered by other tools in the workflow.

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

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

Schema description coverage is 0% and the description does not mention video_id at all. The parameter is just a string, and the description fails to clarify its origin (e.g., from start_video response) or any format expectations. Since coverage is low, the description should compensate but does not.

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 it checks the status of a single video and lists possible statuses (queued, processing, completed, failed) plus additional fields (progress, file_url, error). This distinguishes it from siblings like tegas_list_videos (multiple videos) and tegas_start_video (initiates processing). The verb is implicit but the resource and scope are explicit.

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 'Status of one video' implies it is for a single video, suggesting when to use it over a list tool, but it does not explicitly name alternatives or conditions. It also does not contrast with tegas_wait_video, which might be a blocking alternative. Usage context is implied rather than stated.

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

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

Annotations already indicate read-only and non-destructive behavior. The description adds extra context: the tool is free, and it explains how the returned id feeds into tegas_start_video, including the default behavior. This goes beyond the annotations without contradicting them.

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 sentences with zero waste. It front-loads the cost ('Free.') and immediately gives the core purpose, followed by the critical integration detail. Every word earns its place.

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

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

For a single-parameter, read-only listing tool with an output schema, the description covers everything needed: what it returns, how to use it, and when to skip it. The output schema presumably documents the item structure, so the description need not repeat that. It is complete for an agent to call correctly.

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

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

With 0% schema description coverage, the description carries the burden of explaining the parameter. It lists the accepted languages, which aligns with the enum, and implies the language parameter is used for filtering. It doesn't mention the default value, but the schema provides that. The description adds meaningful semantics 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 states a specific verb ('List') and resource ('voice-over voices') with the supported languages. It clearly distinguishes itself from siblings by explaining the relationship to tegas_start_video, making its purpose 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?

It explicitly explains when to use this tool (to obtain a specific voice id) and when it is unnecessary (when the default voice suffices), going so far as to call it 'optional.' This provides clear guidance on selection and use.

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

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

The description richly documents behavior beyond the readOnlyHint=true and destructiveHint=false annotations: it states the 10-second polling cadence, the three terminal outcomes (completed with file_url, failed with error and token refund, timed_out with last status), and that a 20-30 s video typically takes a few minutes. No contradiction with 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?

The description is compact and front-loaded: the purpose is stated first, then the polling behavior, terminal states, and a helpful estimated duration. Every sentence contributes useful information without 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?

For a two-parameter polling tool with annotations and an output schema, the description covers all key operational aspects: what triggers completion, failure, timeout, how to continue waiting, and expected wall-clock time. Nothing essential for an agent to invoke it correctly 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?

Schema description coverage is 0%, so the description must compensate. It adds meaningful semantics for timeout_sec by explaining that when it elapses the call returns the last status with timed_out=true and can be retried. video_id is not explicitly explained, but its role as the video being waited on is clear from the title and context.

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

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

The description uses a specific verb and resource ('Wait for a video') and details its operation: polling every 10 s until completed, failed, or timed out. The polling-until-terminal behavior distinguishes it from one-shot status tools like tegas_video_status, even 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 description clearly implies this tool is used when you want to block until a video finishes processing, and says to call again after a timeout. However, it does not explicitly state when to prefer this over tegas_video_status or alternative tools, nor does it provide exclusions or preconditions.

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

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

The description adds behavioral context beyond the annotations. It notes the tool 'Free (requires an active plan),' implies a write operation (consistent with readOnlyHint=false), mentions it returns warnings and that the actual duration may differ from requested, and that scenario_id is 'valid for a few days.' These details inform the agent of side effects and constraints without contradicting 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?

The description is relatively long but well-structured, with clear sections for behavior, parameters, return values, and typical flow. It front-loads the key information about plan requirement and the one-call behavior. While every sentence adds value, the length is slightly above the minimum needed, but it remains efficient and organized.

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 all essential aspects: prerequisites (active plan), behavior (no questions, one call), parameter semantics for non-obvious fields, return values (scenario_id, text, episodes, warnings, duration), and the integration flow with sibling tools. Since an output schema exists, the description need not detail the exact structure, but it provides enough for an agent to call the tool correctly and handle the result appropriately.

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?

With schema description coverage at 0%, the description compensates by explaining key parameters: 'duration_sec 5..60' (range), 'aspect 9:16 | 16:9 | 1:1' (enum values), and 'reference_urls: public image URLs of a product/character (or reference_id `ref_...`), optional.' It does not explicitly describe idea, category, or language, but these are either self-explanatory or less critical. The description adds meaningful semantics for the parameters that are most 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?

The description clearly states the tool's purpose: 'Tessa writes a complete video scenario from an idea in one call.' It uses a specific verb (writes), a resource (video scenario), and a clear input (idea). It also distinguishes itself from siblings by outlining a typical flow that includes other tools like tegas_find_heroes and tegas_start_video, so an agent can see where this tool fits in the overall process.

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

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

The description provides an explicit typical flow: 'tegas_write_scenario -> (optional) tegas_find_heroes / tegas_draw_heroes -> tegas_start_video with confirm=false to get the price -> user consent -> confirm=true -> tegas_wait_video.' It also instructs to 'call again with a refined idea if they want changes,' giving clear when-to-use guidance and integration with adjacent tools. It even notes the tool does not ask questions, so users should refine the idea for changes.

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