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

With no annotations, the description carries the full behavioral burden, and it does disclose the most important trait: nothing is persisted, so this is a safe dry-run. It also enumerates what is returned. It stops short of noting that invoking Claude may consume credits/be rate-limited, which matters for an LLM-backed preview.

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?

Two sentences, no filler, with the non-persistence constraint and the returned field list up front and the sibling routing at the end. Every clause earns its place.

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 and no annotations, but the description compensates by enumerating the returned profile fields and stating the absence of side effects. Adding the credit/cost implication would make it fully self-contained for a Claude-backed operation.

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?

One parameter (agent_id) at 0% schema description coverage, so the description must compensate by implying that the parameter identifies the agent whose script is run. That link is implied by 'the agent's script' but never stated, so the meaning added is only partial.

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 action (run Claude on the agent's script) and a concrete artifact (auto-generated ICP profile with offer summary, ICP, topics, LinkedIn queries), and explicitly marks it as non-persisting. This distinguishes it cleanly from sdr_create_search, which is the persisting counterpart.

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?

Explicitly names the alternative and the sequencing condition: use this to review/edit before calling `sdr_create_search`. An agent knows exactly when to pick this tool versus the save variant.

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