BPJ Video Tools

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds meaningful behavior beyond them: it is free, it refuses viral probability/platform approval/algorithm scores, and it will not accept files, URLs or scripts. That scope-limiting context is genuinely useful. It stops short of describing response format or processing behavior.

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

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

Four tight sentences with the scope and negative guarantees front-loaded, and no padding. The underexplained acronym 'BPJ' costs it slightly, but the structure is efficient.

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

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

There is no output schema, and the description gestures at output nature ('editorial experiments') and its refusals, which helps. For a 15-parameter evaluation tool it still leaves the resulting checklist format and the meaning of key fields unclear, so it is adequate rather than 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?

With 15 parameters and 0% schema description coverage, the description carries the full burden of explaining inputs, yet it addresses none of them individually — only a generic 'no files, URLs or scripts' note. The self-descriptive enums (views/follow/try, supported/unsupported, etc.) do some work, but field meaning like 'Fields reach BPJ' is unexplained.

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

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

The description names a specific resource and function — a 'video publishing checklist for six platforms' that produces 'editorial experiments' rather than scores — so an agent can grasp what it does. It does not explicitly distinguish itself from get_video_platform_rules, and jargon like 'Fields reach BPJ' is opaque, keeping it below a 5.

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

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

'Draft self-reports only' establishes the operating mode, and 'no files, URLs or scripts accepted' plus 'missing evidence stays needs-info' set input boundaries. However, it never tells the agent when to prefer this over the sibling get_video_platform_rules or search_manju, leaving usage context implied.

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, idempotent, closed-world read, so the description's real contribution is provenance semantics: it warns that inaccessible or unverified source status stays explicit and that no private platform data is returned. That is meaningful context an agent cannot infer from the hints, though return format and freshness handling remain unstated.

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 with the content scope front-loaded and the provenance caveat second. No filler, though the first sentence is dense enough that it borders on a list-dump.

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 usefully characterizes what comes back (dated evidence plus editorially labelled checks) and its trust posture. The main remaining gap is the default/'all' behaviour and any shape of the returned data, which is minor for a single-parameter read 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?

The description enumerates the six platforms matching the enum values, which is helpful, but the schema has 0% description coverage and the description omits the 'all' option and never states that the parameter is optional. It adds value over the bare enum but does not fully compensate.

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 concrete verb ('Read') and a specific resource: dated official-source evidence plus separately labelled editorial checks across six named Chinese platforms. That content profile clearly separates it from siblings like evaluate_video_publish and search_manju, though the description never plainly says it retrieves 'platform rules' and leans on the name for that framing.

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 stated prerequisites, and no reference to any alternative tool. The six-platform coverage hints at scope but nothing tells an agent when this tool is the right choice versus evaluate_video_publish.

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/openWorldHint/idempotent/destructive, so safety is covered. The description adds genuinely new behavior: no live crawl on a miss, that heat is not equivalent to plays, that source_rank only works with a cohort, and that results can include seasons.

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, front-loaded sentences with no filler; the scope constraint and the key caveats come first. The telegraphic phrasing ('Heat is not plays') borders on cryptic, but nothing is wasted.

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?

It conveys purpose, scope, result-shape hints, and two behavioral caveats, which is meaningful given there is no output schema. But with seven undocumented parameters and no annotation-level detail on filtering, the definition is not complete enough for confident 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?

With 7 parameters and 0% schema description coverage, the description must carry the load, but it only maps query to title/genre/tags and touches sort=source_rank and the cohort requirement. Sort values, limit bounds, channel, category, and officialOnly are left entirely undefined.

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 (Search) and resource (the currently published Chinese AI video/manju catalogue) and lists the searchable dimensions (title, genre, tags) plus what comes back (source dates, official/search/introduction destinations). This is clearly distinct from the sibling tools evaluate_video_publish and get_video_platform_rules, which do not search a catalogue.

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 operational context (read only, no crawl on miss) and one conditional rule (source_rank requires one cohort), which helps the agent compose a valid call. However, it never states when to prefer this tool over alternatives or when not to use it, so usage is only implied.

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