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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description's job is to add context, and it does: the server generates and returns blockId for later edits, and 'No launch' clarifies that adding a task does not start the test. It does not cover failure modes, permission requirements, or what happens on duplicate/position conflicts.

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?

A single wall of text mixes tool purpose, parameter constraints, and three long field-authoring style guides. The sentence 'Preserve supplied or accepted wording unless the user requests a rewrite or delegates wording choices' is repeated verbatim three times, wasting space, and none of the drafting guidance is visually separated from the operational instructions.

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 the description covers the key selection and constraint facts an agent needs plus the unusual drafting conventions for task/scenario/stopCondition. Given the 9-parameter surface, it is complete enough despite the padding; only testId and position semantics are left entirely to the schema.

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 67%, so the schema already documents blockId, isPrototype, task, scenario and stopCondition — and the description's long drafting rules for those fields largely restate what the schema descriptions already say. The one genuinely additive item is the cross-field constraint 'stopCondition requires url', which the schema does not express. Baseline 3 is appropriate.

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 opening sentence gives a precise verb+resource+scope: 'Add a website task or empty task to an existing draft.' It goes further than most siblings by naming the boundary case and the alternative tool ('Use add_test_block for uploaded prototypes or advanced settings'), so an agent can distinguish add_task from add_test_block without opening either 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?

It states when to use the alternative ('add_test_block for uploaded prototypes or advanced settings'), field-conditional rules ('stopCondition requires url', 'Supply url for a website task', 'Omit wording only for an intentionally incomplete draft'), and a scope limit ('No launch'). The tool-selection guidance is real but compressed into one clause and buried among field-authoring conventions, with no guidance on when not to add a task at all.

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