Verify Source

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description does add real behavioral disclosure beyond the schema: the optional tunnel-manager dependency never blocks import, refusals are named and cause-preserving rather than ImportError, and host_loss_reconcile always refuses. However, none of this describes verify_source's own runtime behavior, so it is context without being operation-specific.

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?

Five dense sentences are devoted to package composition and the refusal semantics of other operations, while this tool's own purpose is never elaborated. The content is neither front-loaded with the verify_source operation nor trimmed to what an agent needs to call this tool.

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 not be explained, and annotations cover the safety profile. But for a 35-parameter multiplexing tool, the description omits what verification compares, what a success or mismatch outcome means, and which inputs activate this path — a significant gap for an agent trying to invoke it correctly.

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%, and every parameter carries a "For X:" note, so the schema already documents all 35 fields. The description adds no meaning to the two parameters actually relevant here (destination, expected_sha) and does not clarify how the multiplexed parameter sets dispatch among the eight embedded operations. Baseline 3 applies when the schema does the heavy lifting.

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 opens with "Verify source (rm_remote_workers)", which merely restates the tool name and title without explaining what verification actually entails (e.g., comparing a staged tree against expected_sha at a destination). The remainder describes the module family (remote worker registry, artifact transport, CapacityInventory composition) rather than this tool's specific operation, and never distinguishes it from the sibling rm_remote_workers_stage_source or rm_remote_workers_recheck.

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 guidance on when to invoke verify_source versus sibling tools such as rm_remote_workers_stage_source or rm_remote_workers_recheck, nor any stated prerequisite (e.g., that a source must first be staged). The only conditional behavior discussed (tunnel-manager absence, host_loss_reconcile always refusing) concerns other operations, not this one.

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