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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, so the agent already knows this mutates external state and is not repeatable. The description adds real behavioral context the annotations don't: this triggers a job and blocks waiting on it, which is why resumption exists. It stops short of stating that a timeout leaves a job running server-side (that lives in the schema).

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, zero filler. The capability and its return payload come first, the ordering constraint second, and the critical `source`-must-match rule is parenthetical and easy to scan.

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 correctly carries the return contract, naming each artifact returned. It omits the timeout/resume behavior, but that is fully covered by the input schema, so the omission is minor rather than a hole.

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 the timeout/cap/execution_id resume semantics are already fully documented in the schema. The description adds no parameter-level detail beyond the output contract, so baseline 3 applies.

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?

Specific verb and resource ('Discover a connector's schema') plus an enumeration of the outputs (streams, columns, primary keys, inferred schemas, mappings, namespace). An agent knows exactly what it gets back. It does not distinguish itself from the near-named siblings connector_discover / connector_discover_status, which is the one 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?

Explicit sequencing: run AFTER build_connect_data_source and BEFORE build_bind_data_source, with the hard constraint that a live bind's `source` must equal a discovered stream name. That gives the agent both position in the workflow and the downstream dependency that makes the call mandatory.

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