AiDex

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 the core functionality (capturing screenshots) and key behavioral traits: it returns a file path for immediate reading, overwrites files if they exist (implied by 'Overwrites if exists' in schema), and doesn't require a project index. However, it misses details like potential permissions needed for screen capture, rate limits, or error conditions (e.g., invalid coordinates).

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 the core purpose in the first sentence, followed by essential behavioral details (return file path, no project index). Every sentence earns its place: the first defines the tool's scope, and the second adds critical usage context. It's appropriately sized without redundancy or fluff.

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 (10 parameters, multiple modes) and lack of annotations or output schema, the description is reasonably complete. It covers the main purpose, key behaviors, and integration hint (reading the image). However, it could be more complete by addressing potential side effects (e.g., file system changes) or error handling, which are important for a tool with multiple capture options and no output schema.

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 schema already documents all 10 parameters thoroughly. The description adds minimal value beyond the schema by summarizing the capture modes and mentioning the file path return, but it doesn't provide additional semantic context (e.g., explaining how 'region' mode works interactively or clarifying coordinate systems). Baseline 3 is appropriate given the comprehensive schema.

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 specific action ('Take a screenshot') and enumerates five distinct capture targets (screen, active window, specific window, interactive region, rectangle by coordinates). It explicitly distinguishes this tool from others by mentioning it returns a file path for immediate reading, which differentiates it from sibling tools like aidex_windows (which finds window titles) or aidex_files (which might handle files differently).

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 clear context for usage by listing the capture modes and specifying that no project index is required. However, it lacks explicit guidance on when to use this tool versus alternatives (e.g., when to use aidex_windows first to find window titles for the 'window' mode). The mention of 'immediately Read the image' implies integration with other tools but doesn't name specific alternatives or exclusions.

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