Take an agent's key away

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

Annotations already declare destructive=true, idempotent=true and readOnly=false, but the description adds real value: the access-revocation effect and, importantly, that the change is reversible ('Undoing this lets the agent back in with the same key'). This tells the agent the operation is not permanent, which the annotations alone do not convey.

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 sentences, action front-loaded, each contributing distinct information (effect, key-creation context, reversibility). Slightly more prose than strictly required but no wasted sentences.

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?

For a single-parameter mutation with full annotation coverage and no output schema, the description covers what happens, when to use it, the exclusion, and reversibility. Complete enough to call correctly; naming the undo sibling would close the last gap.

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?

There is a single parameter with 100% schema description coverage ('The agent's name, as the log calls it'). The description adds no format or disambiguation beyond the schema, so the baseline of 3 for fully-documented parameters applies.

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 ('Take an agent's key away') plus the concrete effect ('can no longer reach this workspace'). It is unambiguous about what the tool does, though it never names its obvious counterpart (let_in) among the siblings.

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 clear trigger ('when the person asks') and an explicit exclusion ('Keys are made at the command line with sameway agent add, never here'), which steers the agent away from using this for key creation. It stops short of naming the alternative tool for undoing the action.

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