Cli add

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true, and destructiveHint=false, covering the safety profile. The description adds only that it raises ParameterError on invalid input and returns the POST response object; it does not disclose auth requirements, duplicate-URL handling, or what side effects occur on the collection.

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?

It is a raw docstring dump with Args/Returns/Raises boilerplate; the purpose line is front-loaded, but the heading scaffolding and one-line-per-parameter format add little beyond a flat list. Content density is acceptable for 11 parameters, though not optimized for an agent.

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 an 11-parameter mutation tool with no output schema, the description covers parameters and one error type but omits usage context, authentication, and side-effect/duplicate behavior. It is adequate as a signature reference but thin as invocation guidance.

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?

With 0% schema description coverage across 11 parameters, the description is the sole source of parameter meaning and it covers every one (tag, depth, update, update_all, index_only, overwrite, init, extractors, parser, extra_data). The glosses are terse and partly tautological ('depth: Crawl depth', 'update: Update existing snapshots'), but they still add semantics the bare schema lacks.

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 concrete verb and resource ('Execute archivebox add command') and clarifies the target via 'urls: List of URLs to archive,' so an agent knows this archives URLs. It does not distinguish itself from siblings like archivebox_ingest_snapshots or archivebox_cli_update, which is the only gap.

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?

No statement of when to use this tool versus the many siblings (cli_update, cli_list, cli_remove, ingest_snapshots). The reader must infer from the name alone that this is the ingestion entry point.

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