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

With no annotations, the description carries the full burden and does well: it discloses blocking/wait behavior (poll up to 0-300s), a real side effect (saves the video to disk and returns its path), the non-terminal return shape (status message plus job_id), and error behavior ('failures raise an error'). It omits file naming/location and any auth or rate-limit context, so it is strong but not exhaustive.

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, front-loaded with purpose and timing, then the success path, then the retry path, then failures. Every sentence adds an actionable fact 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?

There is no output schema and no annotations, so the description correctly explains the return values (file path vs. status message with job_id) and the error case. It is nearly complete for a two-parameter polling tool; only the saved file's destination/naming convention is left unstated.

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, and it does for the key parameter by giving wait_seconds' range and default (0-300, default 45) beyond the schema's bare default. job_id's meaning and its reuse across polls are implied rather than defined, which is the only real gap.

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

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

States a specific verb and resource ('Wait for a video job started by start_video') and names the sibling that must precede it, so an agent can immediately place it in the video pipeline rather than confusing it with generate_image or generate_audio.

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

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

Gives a clear precondition (only after start_video) and an explicit repeated-call loop ('call check_video again with the same job_id until the path is returned'). It does not need to name alternatives since none of the other siblings poll a job, but it stops short of stating any when-not condition or termination limit on retries.

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

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

With no annotations, the description carries the full burden and does disclose the critical trait an agent needs: this writes an audio file to disk and returns its path rather than returning bytes. It also documents per-provider output formats (mp3, WAV) and how each backend's payload is mutated. It stops short of auth/error/rate-limit 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?

Purpose and side effect are front-loaded in one sentence, followed by a tight provider-by-provider list where every line adds actionable detail. There is no filler or repetition of the 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?

For a 5-parameter, no-output-schema tool at 0% schema coverage, this covers the essentials including return value and per-provider behavior. Marginal gaps remain: it does not clarify how the required `text` field interacts with fal prompt-based (music/SFX) models, nor what happens when no provider is configured.

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

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

Schema coverage is 0%, and the description compensates thoroughly: it explains the default provider resolution order, the default model and voice per provider, and precisely how the opaque `options` object is applied (merged into the request, shallow-updates generationConfig, becomes {prompt} for fal prompt-based audio). That is meaning the schema cannot convey.

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?

Opens with a specific verb+resource ('Text-to-speech ... Saves the audio file to disk and returns its path'), naming both the operation and its side effect. It is trivially distinguishable from generate_image, start_video, and check_video by modality.

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 provider breakdown gives concrete selection guidance (which backend is default, what each accepts, what output format results), so an agent knows how to pick a route. What is missing is an explicit when-to-use/when-not statement or a named alternative for overlapping cases (e.g. fal prompt-based music/SFX vs speech).

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

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

With no annotations, the description carries the full burden and does disclose the key side effect: files are written to disk and a preview plus paths are returned, so the agent knows this is not a read-only call. It also discloses the non-obvious branch where input_images switches openai to /images/edits. It omits auth requirements, cost, and failure modes for a paid generation endpoint.

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

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

Front-loaded with purpose and return behavior, then a scannable per-provider bullet list. The density is justified by the zero schema coverage, though the provider bullets are heavy enough that an agent must read the whole block rather than skim.

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 6-parameter tool with no annotations, no output schema, and 0% schema description coverage, the description covers the provider/model/aspect_ratio/options/input_images surface and states what is returned. Gaps remain around error behavior, cost, and what happens when multiple providers are configured beyond the 'first configured' rule.

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

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

Schema coverage is 0%, so the description must compensate, and it largely does: aspect_ratio is given explicit per-provider mappings (1:1 -> 1024x1024, 16:9/3:2/4:3 -> 1536x1024), options merge semantics are spelled out including precedence ('options["size"] wins'), model defaults are named per provider, and input_images formats (paths, URLs, data URIs) and roles (edit target vs reference) are defined.

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?

Opens with a specific verb+resource ('Generate or edit an image') and immediately states the observable side effect and return shape ('Saves full-resolution files to disk and returns paths plus a JPEG preview'). This clearly separates it from siblings generate_audio, start_video, and check_video without needing their 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?

Provides clear selection context by documenting the provider default ('first configured of openai, gemini, fal, cloudflare') and the per-provider defaults (gpt-image-2, gemini-3-pro-image, fal-ai/nano-banana-pro, flux-1-schnell), plus when input_images switches to an edit path for openai. There is no explicit when-not guidance or cost/limit exclusion, but the provider routing context is unusually strong.

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

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

With no annotations, the description carries the full burden and largely meets it: it discloses the asynchronous job_id contract, provider defaults, how duration_seconds and aspect_ratio are re-mapped per provider, that duration_seconds is *rejected* for fal, and that options are merged into the provider request. It omits auth requirements, rate limits, and prompt constraints, so not 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?

The first sentence front-loads the action and the async contract, followed by compact per-provider bullets. It is dense but every line carries operative detail; only minor trimming is possible.

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, no-annotation mutation tool this is thorough, and the job_id/polling contract plus provider quirks are covered. An output schema exists so return values need not be described, but there is no mention of validation limits or failure behavior, keeping it just short of complete.

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

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

Schema coverage is 0%, so the description must compensate, and it does: provider enumerates the three backends with defaults, aspect_ratio/duration_seconds translation is spelled out per provider, duration_seconds' fal constraint is documented, options is defined as provider-specific merged keys with examples, and input_image's accepted formats (path/URL/data URI) are given. This adds meaning far 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?

States a specific verb+resource ('Start a video generation job') and immediately distinguishes the two modalities (text-to-video vs image-to-video via input_image). It also names the sibling it hands off to (check_video), so an agent can separate start from poll without opening either 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 explicit workflow guidance: this tool returns a job_id immediately and check_video(job_id) must be called to wait for the result. It also provides per-provider selection guidance with defaults. It stops short of stating when *not* to use it (e.g. vs. generate_image/generate_audio), so a 4 rather than 5.

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