image_alt_text

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

With no annotations the description carries the full burden, and it delivers: it discloses cost ($0.005 USDC/call), latency (p99 10000ms), the internal pipeline (scaled to 800x800, described by Claude Haiku 5.5), and output-shaping behavior (under 125 chars, decorative handling). It stops short of auth requirements or error/failure behavior.

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?

Front-loads the purpose and the output contract before the operational details, and every clause is informative. It is a dense single block, but no sentence is pure filler, so it earns its length.

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?

No output schema exists, so the description must describe returns, and it does thoroughly (short alt text, longer complex-image description, decorative flag, readable text, ready alt="..." attribute). Combined with cost, latency, and processing notes, an agent has everything needed to call it 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?

Schema coverage is 100%, so the schema already documents all four parameters, making 3 the baseline. The description adds only marginal value ('send image_url or image_base64' hints at alternation; 'optional language (e.g. German)'), without new format, size, or constraint details beyond what the schema states.

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+resource (generate alt text for images) and immediately scopes the purpose (WCAG 1.1.1, BFSG, EAA, SEO). It also distinguishes itself from siblings by naming accessibility-check as its complement, so an agent can tell it apart from ocr, image_resize, or accessibility_check.

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 clear context for when to reach for it (web accessibility/SEO, and explicitly 'pairs with accessibility-check, which finds images without alt text'), which is a strong routing signal. However, it offers no explicit when-not-to-use guidance against near neighbors like ocr or image_resize.

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