Connect

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

Annotations already declare a non-destructive, non-open-world write, and the description adds the genuinely non-obvious side effect that both sides are written with an inverse relation on B — telling the agent one call creates two edges. It still omits duplicate/idempotency behavior and any permission or prerequisite requirements.

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 short sentences, zero filler, with the primary action stated first and the side effect immediately after. Every clause carries information.

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?

An output schema exists, so return values need no explanation, but for a mutation tool that silently writes a second edge the description says nothing about duplicates, whether both people must already exist (note the `upsert_person` sibling), or invalid relation handling.

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?

Only `rel` is documented in the schema (33% coverage); `a` and `b` carry no descriptions. The description partially compensates by establishing that a and b are people and that the inverse is applied to B, but it gives no identifier format for a/b and no constraint on rel beyond what the schema already lists.

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 gives a concrete verb+resource ('Record how two people are connected') and implicitly separates itself from the one-directional `link` sibling by stating it writes both directions. It stops short of naming that sibling or any other, so an agent still has to infer the boundary from `link`.

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?

There is no when-to-use or when-not-to-use guidance, and no alternative is named even though `link` and `who_knows` sit in the same sibling set and plausibly overlap. The agent must guess whether `connect` or `link` is correct for a given edge.

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