scout_fetch

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

Despite no annotations, the description fully discloses behavior: scrolling, dumping innerText and AXTree links, writing to a cache file, returning chunked segments, and the caching lifecycle. This gives the agent full understanding of side effects and state.

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 with a line break. It is front-loaded with the main purpose and every sentence provides essential information. No wasted 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?

The description covers all necessary aspects: what it does, how it behaves on first vs subsequent calls, what parameters affect behavior, and output format. Given the complexity (caching, chunking, scrolling) and presence of an output schema, it is 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 coverage is 100% with each parameter described. The description adds meaningful context beyond schema by explaining how start_index interacts with caching ('subsequent calls with start_index read from cache'), which is not in the schema. This adds value.

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 action: 'fetch full page content' with specific details (scroll to bottom, dump innerText + AXTree links, write cache, return chunks). It distinguishes itself from 20 sibling tools by clearly being the one for fetching content.

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 usage guidance: first call scrolls and writes cache, subsequent calls with start_index read from cache. This tells the agent when to use the tool and how the caching works. It lacks explicit when-not-to-use comparisons to alternatives, but the context is clear.

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