artex_call

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

No annotations exist, so the description carries the full behavioral burden. It never states that this is a mutating call capable of DELETE/PUT, never mentions authentication requirements, error behavior, or what preview_chars and overwrite_local actually do. The ARTEX_TRANSFER_DIR note is the one piece of genuine operational context, which is not enough for a 9-parameter HTTP escape hatch.

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?

Four short sentences, front-loaded with the core action and with the escape hatches grouped afterwards. Dense without padding, though the telegraphic fragments ("for any full response use save_as") read slightly under-specified rather than crisp.

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?

For a generic HTTP passthrough with 9 parameters, no annotations, and no output schema, the description covers the primary invocation path but omits response-shaping behavior (preview_chars truncation, save_as file writing, overwrite_local safety). An agent could call it, but not confidently predict side effects.

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 0%, so the description has to compensate and does so partially: it clarifies the path_params/query/body split, states that repeated query values take arrays, and explains that upload_files and save_as are alternatives to inline payloads. However preview_chars (default 6000) and overwrite_local are entirely unexplained despite being non-obvious knobs. Roughly half the parameter surface is left to guesswork.

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?

"Call an exact registered Web route template" gives a concrete verb and resource, and the follow-up sentences carve out what the call is not (multipart handling, streaming, full-response capture). An agent can distinguish this from artex_find_routes and artex_read_events. It stops short of 5 because the phrase "registered Web route template" is never tied explicitly to route discovery.

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 does real routing work: streaming routes go to artex_read_events, multipart goes through upload_files, and full responses go to save_as. What is missing is the precondition that the route must first be located via artex_find_routes, and no guidance on when a non-HTTP sibling would be preferable.

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