invoke_capability

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

No annotations, so the description carries the burden and largely does: it discloses the origin/prefix scoping granted by the handle, the per-mode argument shapes, the SSH byte range (1-4096), and a replay/ejection warning. It does not cover error behavior or what a response contains, which is acceptable given an output schema exists.

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?

Front-loads the core action in the first sentence, then dispatches mode by mode with no filler. Dense and long, but this is a 7-parameter polymorphic tool and every clause conveys a rule the agent needs; the SSH byte range is the only slightly noisy detail.

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 7-param, 0%-coverage, nested-object schema with an output schema present, the description covers mode selection, optionality, scoping and a safety rule. It omits how handles are obtained and any error/failure semantics, which are the remaining gaps.

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 0%, so the description must compensate, and it does: it maps handle, method, path, query, headers, body_base64 and payload onto their respective modes and marks which are optional. It does not spell out the payload/method mutual exclusion that the schema encodes, leaving one inferential step.

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 ('invoke') and resource ('the exact capability named by handle'), and goes further by breaking the resource into dispatch modes (http_request, http_broker, attestation, SSH). It never names the siblings, but the action/read distinction against describe_capability and list_capabilities is obvious from the verb alone.

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 per-mode guidance: http_request takes only handle, http_broker takes method/path plus optional query, headers, body_base64, attestation takes a base64 payload, SSH takes one unframed base64 SSH-agent message. Adds an explicit 'never replay an ambiguous or cancelled invocation' rule. It stops short of saying when to prefer this over the describe/list siblings.

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