Stock Photos & Videos

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

No annotations are provided, so the description carries the full burden. It discloses the critical behavior of returning the download_link and the required ordering, but does not mention other return details, potential errors, or required permissions. This is adequate but leaves some behavioral aspects 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 concise sentences with front-loaded purpose, followed by a clearly marked critical usage note. Every sentence earns its place without redundancy or clutter.

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 one-parameter tool with no output schema, the description provides the essential context: what it does, when to use it, and the key output (download_link). It stops short of fully describing the response structure or error conditions, but is sufficiently complete for the tool's complexity.

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 description covers 100% of the parameter ('The ID of the media (photo or video)'). The tool description adds little beyond restating the ID's purpose, so it relies on the schema. Baseline of 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 clearly identifies the action ('Retrieves detailed information') and the specific resource ('stock photo or video by ID'). It explicitly distinguishes itself from sibling tools by requiring a prior search and focusing on a single media 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?

Provides explicit workflow guidance: use this tool AFTER get_photos or get_videos to obtain the download_link. This clearly states when to use it and names the alternative search tools, making the intended usage unambiguous.

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 behavioral disclosure burden. It reveals a key behavior: search results do NOT include a download link, and the follow-up tool is required. It does not mention authentication, rate limits, pagination behavior, or result ordering, but the disclosed limitation plus metadata mention give moderate transparency.

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 sentences, front-loaded with the action and results, with the critical limitation clearly flagged via [CRITICAL]. Every sentence adds value, and formatting improves scannability.

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 tool has 4 parameters, no output schema, and no annotations. The description conveys the response is a list with metadata (width, height, aspect ratio) and a missing download link, plus the required next step. It could enumerate the exact return fields or pagination defaults, but it is substantial for a stock-photo search 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 input schema has 100% parameter description coverage, including enums for 'size' and 'orientation'. The description adds no parameter-specific detail beyond the schema, so it sits at the schema-covered baseline.

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 a specific verb ('Search for stock photos on Pexels') and clearly states it retrieves a list matching a query. It distinguishes from the sibling 'get_videos' by topic, and the workflow involving 'get_media_detail' is identified. This is a clear, focused purpose statement.

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 context: use this tool to search stock photos, then pass the selected 'id' to 'get_media_detail' for the download link. It does not explicitly exclude video searches or compare to 'get_videos', but the mention of the alternative retrieval tool serves as solid usage guidance.

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 discloses a critical behavioral trait not obvious from the schema: 'The search results do NOT include a download link.' This is a significant gotcha that prevents misuse. However, since no annotations are provided, the description carries the full burden; it does not mention other potential behaviors like pagination or rate limits, though the schema covers the page parameter.

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 fairly concise with only three sentences. However, the first two sentences are somewhat redundant (both mention searching/retrieving videos). The [CRITICAL] marker is useful and front-loaded enough, but the repetition prevents a perfect score.

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 moderate complexity (4 params, no output schema), the description covers the essential use case, return metadata, and the critical follow-up requirement. It could be more explicit about the response structure (e.g., presence of the 'id' field) but it's implied. No output schema exists, so this is reasonably 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 description coverage is 100% (all four parameters: query, page, size, orientation have descriptions). The description adds no additional parameter semantics beyond the schema, so the baseline score 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 clearly states a specific verb and resource: 'Search for stock videos on Pexels' and 'Retrieves a list of high-quality stock videos matching a given query.' It also differentiates from the sibling tool 'get_media_detail' by explicitly noting that the download link is obtained through that tool, not this one.

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 guidance on when to use this tool vs an alternative: 'You must pass the id of the chosen video to the get_media_detail tool to retrieve the actual download_link.' This clearly directs the agent to use get_media_detail when a download link is needed, establishing the proper workflow.

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 transparency burden. It clearly indicates a read operation ('retrieves') but does not disclose whether the call itself consumes rate limit, requires authentication, or has other behavioral nuances. The description adds some value by specifying returned metrics, but could be more transparent about potential side effects.

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, front-loaded with the action and resource, and the usage note is a single clause. Every word contributes, and it is easily 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?

Given the tool's simplicity (no params, no output schema), the description provides a clear enough understanding of the behavior and return content (used and remaining requests). It could elaborate on the exact response structure, but for a rate-limit monitor, it is sufficient.

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 reflects that with 100% coverage. The description does not need to explain parameters, and the baseline of 4 for zero-parameter tools 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 clearly states the tool's purpose: 'Retrieves the current user's API rate limits, including requests used and remaining requests.' The verb 'retrieves' and the resource 'API rate limits' are specific, and the mention of used/remaining requests distinguishes it from the sibling media-related tools.

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 context with 'Use this to monitor your quota,' telling the agent when to invoke it. It does not explicitly name alternatives or exclusions, but the sibling tools are all media-related, so the usage context is clear enough.

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