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

With no annotations, the description carries the full burden. It does disclose real internals — retries, validation, min-size filtering, content-hash dedup — which is more than most. However it never says that files are written to disk, where, or under what permissions/overwrite semantics, so the mutation side effect is left implicit.

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 core action front-loaded and the behavioral details second. No filler, though the second sentence is a dense list that could be slightly more scannable.

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, but with zero annotation coverage and zero schema description coverage, the description should compensate more. It omits the output directory semantics (a write target), the items payload format, and concurrency behavior, leaving the agent guessing at the most consequential parameters.

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% across 5 parameters, and the description only semantically covers the minimum-size filtering (min_width/min_height) and dedup behavior. It says nothing about the required 'items' shape, output_dir, or max_concurrency, leaving most parameters undocumented in both places.

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?

Clear verb+resource ('Download ranked image candidates') and it explicitly ties its input to the sibling search_images, so an agent can place it in the pipeline. It does not, however, distinguish itself from other retrieval siblings such as fetch_creator_images or inspect_item.

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 'returned by search_images' implies this is the follow-up step after search_images, which is useful implied usage. But there is no explicit when-to-use, no when-not-to-use, and no statement about what to do if the candidate set is stale or needs re-fetching.

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 discloses real behavior beyond structure: default is fast account-only retrieval with no semantic/visual filtering, filter_mode=optional degrades when the local model is unavailable while required fails closed, downloads are bounded by max_posts/max_images, and resume=true continues pending media. It omits auth/rate-limit and on-disk overwrite behavior, but the safety/fallback semantics are well covered.

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?

Long but dense and front-loaded: platform/identifier rules come first, then media_type and filtering behavior, then bounds and resume. Nearly every sentence carries an actionable constraint, though it could be tightened slightly.

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 22-parameter tool with no annotations, the description covers the main selection workflow, fallback logic, and bounding parameters; return values need not be explained since an output schema exists. The remaining gap is the undocumented minority of parameters (time range, quality, concurrency, safe mode).

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% across 22 parameters, so the description must compensate. It meaningfully explains creator_id, creator_name, profile_url, media_type, content_query, filter_mode, max_posts, max_images, and resume, but leaves sort, since, until, cursor, min_width/min_height, output_dir, quality_mode, max_concurrency, include_video_covers, safe_mode, and download completely undocumented.

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 (download creator media), names the three platforms, and explicitly rules out a wrong interpretation ('NOT a post ID'), which helps place it against sibling tools like search_images/inspect_item.

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 per-platform identifier rules (creator_id/handle/UID/sec_uid, creator_name, profile_url), a concrete fallback ('retry with the complete douyin.com/user/<sec_uid> URL because it is more stable'), and selection guidance for content_query and filter_mode.

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?

No annotations are provided, so the description carries the full behavioral burden. It doesn't disclose whether this is read-only, whether it hits rate limits, requires auth, or what 'image candidates' actually means operationally. Given the inspection tool has a return side effect only in reading, this is a notable gap.

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 efficient sentence that front-loads the action and resource, then names the return content. 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?

Output schema exists, so the return content ('image candidates') needn't be fully explained. However, with no annotations and 0% parameter coverage, the description leaves both required parameters and safety profile under-specified for an inspection 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 0% with 2 required parameters, so both parameters are undocumented in both schema and description. The description mentions 'by ID' for item_id but says nothing about the required 'platform' parameter or its expected format.

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 ('Inspect') and resource ('platform item by ID') plus the return content ('image candidates'). Clear enough to distinguish from siblings like search_images or fetch_creator_images, though it doesn't explicitly name those alternatives.

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?

Implies usage via 'by ID' (i.e., when you already have a specific item identifier), but offers no explicit when-to-use vs search_images or fetch_creator_images guidance and no 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?

No annotations are provided, so the description must carry the behavioral burden. It does add real context — results reflect 'effective availability' resolved through source projects or legacy adapters, which tells the agent output depends on configuration — but it says nothing about safety profile, ordering, or whether adapters must be enabled first.

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 waste. The trailing clause 'through recommended source projects or optional legacy adapters' is slightly jargon-dense but is the only place that nuance is conveyed, so it 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?

With no parameters and an output schema present, the description need not explain return values, and it supplies the one non-obvious semantic point (availability is mediated by source projects/adapters). It is nearly complete; a note on what 'supported' spans or a pointer away from list_sources would close the 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?

The tool takes zero parameters and the schema declares an empty object, so there are no parameter semantics to document. Baseline 4 applies; the description correctly adds no redundant parameter chatter.

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 ('List supported platforms') and adds a meaningful qualifier about how availability is resolved (recommended source projects vs. legacy adapters). It does not, however, differentiate itself from the sibling list_sources, which an agent could plausibly confuse it with.

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 verb 'List' — there is no explicit statement of when to call this versus list_sources or the image-oriented siblings. The mention of 'recommended' vs 'optional legacy' adapters hints at relevance but does not define a selection condition.

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 discloses useful system context — sources drive candidate recall and AI ranking is handled server-side — which clarifies the tool's role, but says nothing about permissions, whether the returned configuration status can change, or how results are ordered.

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, no filler, with the core action front-loaded and the explanatory context placed second. Every clause contributes.

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 parameterless read tool with an output schema present, the description need not explain return values. It covers what the tool lists and why sources matter; the only minor gap is the absence of any guidance on when in a workflow to call 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 of 4 applies. There is nothing for the description to disambiguate, and it correctly does not invent parameter detail.

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 ('List recommended source projects') plus an extra dimension ('their configuration status'). Siblings are in unrelated domains (image search, platforms, feedback), so no explicit differentiation is needed, but the description does not name what distinguishes this listing from list_platforms beyond topic.

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 rather than stated: an agent infers it should call this to discover which sources exist before searching. The second sentence gives purpose context ('Sources are used for candidate recall') but offers no when-to-use condition, prerequisites, or alternative tools to consider.

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?

There are no annotations, so the description carries the full behavioral burden. It mentions one side effect (media_type=videos can return original video files) but says nothing about authentication, rate limits, caching, safety filtering, or what happens to downloaded files. For a 14-parameter search tool that can write to an output directory, this leaves major behavior undisclosed.

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, no filler, and the creator-query routing rule is front-loaded after the core capability. It is compact and readable. It could be even tighter, 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?

For a 14-parameter tool with an output schema, no annotations, and 0% schema description coverage, two sentences cannot carry the necessary context. The description fails to explain what most parameters do, what the return shape is, or how this tool differs from its six 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?

Schema description coverage is 0% and 13 of 14 parameters have no textual explanation anywhere. The description only partially touches media_type ('videos can return original video files') and the query syntax, leaving download, safe_mode, use_cache, platforms, quality_mode, retrieval_mode, and the remaining eight parameters completely opaque.

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 ('Search') and resource ('social platforms') and even names the unit of input (keyword, content ID, post URL). It also carves out a special routing behavior for creator queries. It does not, however, compare itself to siblings like fetch_creator_images or download_images, so an agent must still reason about which tool owns which scenario.

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 it by describing input types and a special query syntax, but it never explicitly says when not to use it or which sibling to prefer for adjacent tasks such as direct creator fetches or downloading. A reader can infer the main use case but not the alternatives.

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 it does disclose two useful traits: the feedback is 'local' (not global/remote) and it 'reranks the same type of future results'. It omits whether repeated submissions overwrite prior feedback, permission requirements, or whether the write is reversible.

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 action front-loaded and the consequence second. 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?

An output schema exists so return values need not be described, but a mutation-style tool with 5 undocumented parameters and no annotations is under-specified. The description should clarify what candidate_id vs image_url mean and what 'local' scope implies for the agent's data.

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% across 5 parameters (4 required), and the description explains none of them. Only the 'accepted' boolean is vaguely inferable from 'whether a returned image matched the user's intent'; query, platform, candidate_id, and image_url are left entirely undocumented.

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 ('Record') and a concrete subject ('whether a returned image matched the user's intent'), which is clearly distinct from search/fetch/download/list siblings. It stops short of naming a sibling or explicitly contrasting scope, so it is clear but not maximally differentiated.

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 second sentence implies the tool is called after a result is returned and that it feeds future reranking, which hints at context. However, it never states when to call it versus doing nothing, whether it must follow a search_images call, or any prerequisites, 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.