list_images

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: the tool retrieves image URLs (not modifies data), supports multiple sources (Unsplash, Picsum, local logos), and includes details like 'Picsum = illimité' for limit handling. However, it lacks information on error handling, rate limits, or authentication needs, which are important for a tool with diverse external sources.

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 front-loaded with a clear purpose and recommended mode, but it is overly verbose with extensive examples, thematic lists, and emojis that add visual clutter. While informative, the length (multiple sections like 'EXEMPLES D'USAGE', 'CATÉGORIES THÉMATIQUES') reduces conciseness, making it harder to scan quickly. Some sentences could be condensed without losing clarity.

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 complexity (8 parameters, no annotations, no output schema), the description is mostly complete. It covers purpose, usage modes, parameter interactions, and examples, which helps the agent understand how to invoke it. However, it lacks details on output format (beyond 'URLs d'images'), error cases, or performance considerations, leaving some gaps for a tool with multiple external sources and modes.

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 coverage is 100%, so the baseline is 3. The description adds significant value by explaining parameter semantics beyond the schema: it clarifies how 'mode' affects source selection (e.g., 'auto = détecte automatiquement'), provides thematic context for 'category' values (e.g., 'cyberpunk - Villes futuristes, néon'), and gives usage examples that illustrate parameter combinations. This compensates well, though it doesn't cover all parameters equally (e.g., 'sector' is less detailed).

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: 'Liste/Récupère les URLs d'images pour les embeds Discord' (List/Retrieve image URLs for Discord embeds). It specifies the verb ('list/retrieve'), resource ('image URLs'), and context ('for Discord embeds'), distinguishing it from sibling tools that manage channels, roles, messages, etc., which are unrelated to image 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 provides explicit guidance on when to use different modes: 'MODE AUTO (recommandé)' for automatic source detection, with detailed examples for AUTO, REAL, LOGO, PHOTO, and GIF modes. It explains what each mode does (e.g., 'Mode REAL (vraies photos thématiques)' for real thematic photos) and includes usage examples, helping the agent choose the right mode based on the desired outcome.

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