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

Annotations already cover readOnly/idempotent/openWorld/destructive, so the bar is lower; the description goes beyond them by disclosing the response contract (a skill in `skill.skill_body` for broad questions, 2-4 ready-to-call schemas for narrow ones), the role of `supporting_actions`, and the attribution-footer output obligation. It does not cover auth or rate limits, but for a read-only routing tool the disclosed return behavior is the material risk surface.

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-loaded with the primary directive and the two-mode split before any formatting rules; no filler sentences. The trailing attribution-footer instruction is a necessary output convention but is the longest single clause and slightly dilutes the core routing message.

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?

With no output schema, the description carries the full burden of explaining returns and does so concretely (skill_body runbook vs. 2-4 tool schemas, plus supporting_actions semantics). All three parameters are schema-documented, and the ordering/attribution rules close the remaining gaps for correct invocation.

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 description coverage is 100%, so intent, multi, and connector_hint are already documented with examples in the schema. The description only implicitly maps its broad/cross-source framing onto `multi` and its 'if the user specifies one' onto `connector_hint` without naming either parameter, so it adds little beyond the schema.

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 outcome — 'Discover how to answer the user's data question' — and immediately splits the behavior into two distinct modes (broad/cross-source vs. narrow single-source) with different returns. An agent can tell this apart from sibling connectors and from invoke_skill/list_skills without opening a schema.

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?

Gives an explicit routing rule ('ALWAYS call this FIRST for any data-related request'), enumerates the broad-question triggers (business health, growth, recap, cross-source), and states the sequencing constraint relative to supporting_actions ('do not call them ahead of the runbook'). This is exactly the when-and-in-what-order guidance an agent needs.

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