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

With no annotations, the description carries the full burden and does convey that this is a read of key-scoped account data and what fields come back. It does not state that it is side-effect free, what happens with an expired or unentitled key, or whether values are cached/stale — meaningful gaps for a no-annotation tool, but the entitlement contents are a genuine addition.

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, colon-front-loaded with the resource first and the three returned data points after. No filler, no repetition of the tool name.

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

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

No output schema exists, so the description must enumerate return values and it does so concretely (minutes remaining, reset date, agent-captioning flag). What remains unstated — error behavior for bad keys and whether reads are free — is minor for a zero-parameter status 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?

Zero parameters, so the baseline of 4 applies; the description correctly implies the API key is the implicit input rather than a parameter. Nothing further is needed on this dimension.

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 the exact resource (Cuecaps plan tied to the API key) and enumerates what it exposes: remaining cloud minutes, reset date, and agent-captioning entitlement. This is unmistakably a billing/entitlement lookup and cannot be confused with caption_video, transcribe, or list_styles. It stops short of 5 only because there is no explicit verb phrasing (e.g. 'retrieve').

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 — an agent can infer it should call this before burning minutes or to check plan entitlement, but the description never says when to call it, when not to, or what to do if the key is invalid. No alternatives are named, though the sibling set makes the boundary fairly obvious.

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

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

With no annotations, the description carries the burden and does meaningful work: it discloses that the video stays local, that cloud minutes are consumed, that a plan tier (Creator/Pro) is required, and it enumerates the returned fields. It stops short of stating failure modes (e.g. what happens if minutes run out) or time cost of rendering.

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 dense sentences, front-loaded with the purpose and side effect, then return values and plan gating. Everything earns its place, though the enumerated output-format list partially duplicates the schema's output parameter.

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 the description compensates by naming exactly what is returned (file, duration, engine, cloud minutes, studio link). With 13 parameters all documented in the schema and the privacy/plan constraints stated, an agent has everything needed to call it correctly.

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

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

Schema description coverage is 100%, so per-parameter meaning is already fully documented, including the nuanced engine, output, and out_path descriptions. The description restates the choice of output formats and the default filename convention but adds no syntax or constraint detail beyond the schema, so 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?

States a specific verb and resource ('Captions a local video or audio file') plus the exact renderer, output formats, and side effect of writing a file next to the input. It is clearly distinguishable from the sibling transcribe (which would just produce text) because burning in captions/overlays is called out 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?

Usage is implied by the description (local file on this machine, captioning outputs), but there is no explicit when-to-use rule and no routing against the siblings. An agent gets no statement such as 'use transcribe instead when you only need the transcript' or 'use studio_link to fine-tune after rendering'; the list_styles pointer lives in the schema, not the description.

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 return payload (id, name, appearance), which is the relevant behavior for a static lookup. It stops short of confirming it is a side-effect-free read or whether results are fixed at ten.

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

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

A single front-loaded sentence with no filler; every clause (count, returned fields, downstream use) 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?

No output schema exists, so the description must describe return values, and it does so for all three fields. For a zero-parameter enumeration tool this is nearly sufficient, though a hint about ordering or stability would complete it.

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

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

The tool takes zero parameters, so the baseline is 4. The mention of 'the id to pass as style' adds cross-tool meaning about how the returned identifier is consumed, which the empty 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?

Names the specific resource (the 10 Cuecaps caption styles) and enumerates what comes back: id, name, and visual description. It is clearly distinguishable from the siblings (which are link/auth/video/transcription tools), but it never uses an explicit verb like 'list' — the scope is inferred from the title-style phrasing.

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 'the id to pass as style' implicitly signals the downstream use with a captioning tool, which is useful routing context. However, it states no explicit when-to-use condition or exclusion, and never names a sibling tool to pair it with.

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; it does add real behavioral context (no API key needed, available on every plan, processing/export happens client-side in the browser). It omits the most important behavior for a link tool: that the call returns a URL rather than rendering anything, whether the link expires, and whether any server-side state is created.

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, and the core idea (a preconfigured link handed to the user) is front-loaded. The phrasing 'opens set up with these settings' is slightly awkward and could be tightened into an explicit statement of what is returned.

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?

All six parameters are optional and fully documented in the schema, and there is no output schema, so the description should explain the returned artifact. It explains the surrounding workflow but not what the caller actually gets back, which is the one thing an agent most needs before invoking a link generator.

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% and four of six parameters have enums, so the schema already does the explanatory work. The description adds nothing about the settings themselves beyond the vague phrase 'with these settings', so 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 conveys that this produces a preconfigured Cuecaps studio link and that the end user finishes the job (drop in video, export in browser), but it never uses an explicit verb like 'generate' or 'returns a URL'. It also gives no differentiation from the sibling caption_video, which is the obvious alternative for producing captioned output.

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?

'Works on every plan, with no key' plus 'the user drops in their video and exports in the browser' implies the hand-off use case, so an agent can infer when this is appropriate. However, there is no explicit statement of when to choose this over caption_video or transcribe, and no exclusions or prerequisites beyond the licensing note.

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. It usefully discloses that no file is written, what comes back (start/end seconds, SRT text, engine), and that access is limited to Creator and Pro plans, but says nothing about duration limits, that the cloud engine uploads content, or that cloud minutes are consumed at cost.

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 short and every sentence carries some information, but the opening fragment is not front-loaded with an action verb, and 'Creator and Pro' is compressed to the point of being ambiguous about what it gates.

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

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

With no output schema, the description does describe the return payload, which is the main job here, and the schema covers all four parameters richly. However, with zero annotations the behavioral picture (file size/length limits, cloud upload implications, fallback when minutes run out) is only partially filled in.

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 explains path, lang, engine and keyterms in detail. The description adds no parameter-level meaning beyond that, so the baseline of 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 conveys the resource (a local video/audio file) and the payoff (word-level timings, SRT text, engine name), but it never states the action in a verb – it is a sentence fragment that only makes sense because the tool name is 'transcribe'. It does not clearly separate itself from caption_video beyond 'Writes no file'.

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 explicit statement of when to use this versus caption_video, list_styles or studio_link. The only routing hint is the implicit 'Writes no file', which is a side effect rather than a usage rule, and 'Creator and Pro' is unexplained gating without naming the alternative for other plans.

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