compute_targets_list

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the trailing 'Read-only' adds nothing beyond structured data. The description does add useful behavioral context by naming the two returned payload categories (target config and device_matrix capability map) and disclosing CUDA state, but it says nothing about response shape or whether the matrix is static.

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?

One front-loaded sentence with no filler, and the two payload categories come before the read-only note. The phrasing is telegraphic ('device_matrix: which operations support...') but every clause carries information.

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?

There is no output schema, so the description must carry the return-value burden, and it only names the two payloads without describing their shape or fields. For a read-only discovery/reference tool this is adequate minimum-viable coverage but leaves the agent guessing at what it will actually receive.

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 100%, and the single 'request' wrapper's nested execution fields are exhaustively annotated, including which operations support prefer_gpu/require_gpu. The description adds no meaning beyond that schema, so the baseline of 3 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?

Names the resource precisely: configured compute targets (local CPU, CUDA state) plus a device_matrix of GPU-capable operations. That is a specific, non-tautological purpose an agent can distinguish from siblings like diagnostics or properties_reference, though it never contrasts itself with those siblings explicitly.

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?

Usage is only implied: the schema's device_policy and target_id fields point back to compute_targets_list, so an agent can infer this is the discovery call to make before configuring execution. The description itself states no when-to-use condition, no prerequisite, and no alternative.

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