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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds the useful default (`distinct` defaults true) and the reversibility of the mark. It says nothing about validation failure behavior when the two entities are of different types or don't exist, which is the main behavioral risk here.

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, front-loaded with the operation and its default before the per-type locator rules. Dense but every clause carries information; the 'focusTest + otherTest or distinctTest' phrasing is terse to the point of slight ambiguity.

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?

No output schema, 11 optional parameters and low schema coverage mean the description should carry more weight. It covers the dominant entity types and the unmark path, but leaves minor entity types, credential parameters, and error behavior unaddressed. Adequate to call correctly for the common cases, not complete for the full surface.

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 coverage is only 18% across 11 parameters, so the description must compensate — and it largely does by mapping entity types to the locator families (focusTest/otherTest/distinctTest vs. ordinalIds vs. event titles). The one real gap is the relationship between `distinctTest` and `focusTest`/`otherTest`, which stays ambiguous, and several enum entity types (EXTERNAL, SCREEN, API_OPERATION, etc.) have no stated locator.

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 resource: 'Mark or unmark two same-type entities as distinct.' The scope constraint ('two same-type entities') plus the default value of `distinct` makes the effect concrete. It doesn't need to distinguish itself from a close sibling since none of the listed siblings performs this operation, but it also doesn't say what 'distinct' means semantically in the domain.

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 explicit routing guidance per entity type: TEST uses TestLocators, STORY/SCENARIO/ISSUE use ordinals, EVENT uses titles. It also states how to undo the operation ('Set distinct=false to remove a mark'). No exclusions or preconditions are stated, but for a tool with no near-equivalent siblings the context is sufficient.

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