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

Annotations already declare destructiveHint=true and idempotentHint=true, so safety is covered. The description adds state preconditions beyond the annotations — both blocks must already exist in this draft, and cross-test or launched-run joins are rejected — which is exactly the extra behavioral context an agent needs. No contradiction with the annotations.

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?

Three tight sentences, front-loaded with the effect before the clearing rule and the constraints. Not a word of padding.

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, and the destructive annotation plus stated preconditions cover the mutation risk. The description is adequate for a draft-scoped link tool, though it says nothing about the optional construction payload beyond what the schema provides.

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?

At 60% schema description coverage, the schema already documents fromBlockId, construction, and expectedRevision in detail. The description only reinforces fromBlockId's null-clearing behavior; testId and blockId receive no semantic detail from either source. Baseline 3 is appropriate since the schema carries most of the load.

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 states a concrete effect — resuming a task from the nearest preceding website task with the same URL — which maps to setting a block continuation. It is clear and specific about what happens, but it does not name a sibling or otherwise disambiguate from tools like update_test_block or set_test_construction.

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?

"Use null to clear" tells the agent how to remove a continuation, and the constraint "cannot join separate tests or launched runs" clearly states a when-not condition. It stops short of naming an alternative tool for cases outside the draft, so it is not a full when/when-not/alternatives treatment.

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