add_source

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

With no annotations, the description carries the full burden and does disclose real traits: it runs without a shell, auto-strips Gutenberg boilerplate, sets a tier, requires user confirmation before downloading, and enforces a license=public-domain gate for non-PD hosts. It omits idempotency/conflict behavior and permission requirements, so it is strong but not exhaustive.

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 core action, then uses pipe delimiters to compactly present the three input modes, safety rule, and next step. Dense but every clause earns its place; no filler.

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 10-parameter mutating tool with no annotations and no output schema, the description covers the workflow and key safety/license rules but leaves several parameters and the result of ingestion undocumented. Adequate but with material gaps given the tool's complexity.

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 only 30% across 10 params, so the description must compensate. It usefully explains url (fetch + strip), text (insertion), path (local file), tier assignment, and the license gate, but leaves basename, back_from, front_until, and advisor_dir unexplained in both schema and description. Partial compensation only.

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 and resource ('pull a source into the advisor's sources/') and enumerates the three intake modes (url/text/path). It also names the follow-on sibling build_advisor, so the agent can distinguish ingestion from corpus assembly. Slightly dense with parenthetical detail, but the core action is unambiguous.

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?

Guides mode selection (url=fetch+strip, text=insertion, path=local file) and routes the next step to build_advisor. It also states a precondition ('confirm the download with the user') and a gating rule (non-PD host requires license=public-domain). It stops short of naming explicit when-not conditions or alternative ingestion siblings.

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