holiday-photo-plus-2

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

With no annotations, the description carries the full burden and does so well. It reveals that the tool returns a hosted URL rather than displaying the image directly, that the agent must create an HTML artifact, and that the artifact must be a single <img> tag. This goes beyond the schema and sets correct expectations for the agent's follow-up actions.

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 three sentences, each with a distinct purpose: what the tool does, mandatory follow-up action, and prerequisite discovery. It is front-loaded with the main purpose and contains no filler or redundant statements.

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 (one param, no output schema), the description is complete. It explains the return value (hosted URL), the required next step (HTML artifact with <img> tag), and how to obtain valid photo IDs via list_photos. No essential context is missing for an agent to invoke and use the tool 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?

The schema already provides a clear description for photo_id ('Identifier of the photo, e.g. 'sunset'). The description adds value by telling the agent to use list_photos to discover valid IDs, reinforcing the parameter's meaning and source. Since schema coverage is 100%, the description's additional guidance earns a score above 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 clearly states the tool's function: 'Display a holiday photo to the user by creating an HTML artifact that embeds the photo from its hosted URL.' It uses a specific verb ('display') and identifies the resource (photo) and output mechanism (HTML artifact), distinguishing it from the sibling tool list_photos.

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 steps: 'After calling this tool you MUST create an HTML artifact...' and 'Use list_photos first to discover valid IDs.' It also explains what not to do ('Do not write a prose description, caption, or commentary'), giving clear when-to-use and how-to-use 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?

With no annotations provided, the description carries the full burden. It discloses that the tool lists photos and returns their ID and description, which implies a read-only operation, but it does not address pagination, sorting, or any access requirements. For a simple list operation, this is acceptable but not comprehensive.

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 a single, tight sentence that front-loads the action ('List'), specifies the scope ('every available holiday photo'), and defines the output fields ('ID and description'). No unnecessary words.

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 parameters, no output schema), the description explains the output ('ID and description') and the scope ('every available'). It could mention ordering or pagination, but the description is largely complete for a basic listing 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 zero parameters, so schema coverage is trivially 100%. The description does not need to add parameter details. Per the rubric, a baseline of 4 is appropriate when there are no parameters.

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 function with a specific verb ('List'), the resource ('every available holiday photo'), and the return scope ('ID and description'). It distinguishes from the sibling 'get_photo' by emphasizing the plural 'every available' versus a singular retrieval.

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 usage for enumerating all photos but does not explicitly explain when to use this tool versus 'get_photo'. The phrase 'every available' suggests this is for listing all photos rather than retrieving one, but no alternatives or exclusions are mentioned.

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