capability_unregister

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

Annotations already flag destructiveHint=true, and the description goes well beyond them: deletion is immediate and hot, it tears down the adapter instance and all its tools, it bypasses the allowWrite permission gate, and a missing id returns E_NOT_FOUND. These are exactly the operational consequences an agent needs before invoking an irreversible delete.

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?

Four short, dense sentences with the destructive action front-loaded and no filler. Every clause carries distinct information: mechanism, effect, permission model, and failure mode.

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 destructive tool with no output schema, the description covers the mechanism, the blast radius, the auth/permission implication, and the failure mode. Nothing an agent needs in order to call it safely is missing.

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?

With one required parameter at 0% schema description coverage, the description should carry the load. It does add error semantics for the id (missing id yields E_NOT_FOUND) and implies the id names a registered capability, but it never states the id's expected form or provenance (e.g., the name returned by capability_register). Partial compensation only.

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+resource ("Hot-delete a live capability") and adds scope details: removes the adapter instance and its tools immediately. It also names the sibling path it mirrors ("same path as mcp_remove"), so an agent can distinguish it from mcp_remove and capability_register without opening any 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?

Gives clear routing context: it is the control-plane path that does not require allowWrite, whereas the Console REST path requires confirm:true. That tells the agent when this variant is the right call. It stops short of an explicit when-not/alternative statement (e.g., use capability_configure for edits), so it is clear but not fully prescriptive.

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