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

Adds two pieces of context the annotations don't carry: the operation requires explicit founder confirmation, and it is free. However, the effects of a stop (does the test end permanently, are its results retained) are not disclosed, which matters even with destructiveHint=false.

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 front-loaded sentence covering both modes and the approval gate, with no filler. Minor noise from the trademark symbol and the trailing "Free."

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?

Adequate for a two-parameter mutation with no output schema: modes, gate, and cost are covered. It is silent on what stopping does to test state or results and whether either action is reversible, which an agent should know before calling.

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?

The description supplies meaning for the enum value "extend" (grow by a third) that the schema leaves bare, which is useful. The "id" parameter and the stop semantics remain documented only in the schema or not at all, so it only partially compensates for 50% coverage.

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?

Names a specific verb pair on a named resource: grow an existing Bullseye Test by a third (extend) or stop it (stop). It implicitly distinguishes itself from siblings like bullseye_add or bullseye_read by operating on an already-running test, but never names those siblings outright.

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 a concrete trigger for the extend path ("after a too-close read") and a precondition for both paths ("on the founder's yes"), which is real when-to-use guidance. It does not name alternative tools or say what to do if the founder has not yet approved.

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