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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral context: a required Last Price credential and the concrete failure mode (403 refusal) for sandbox keys from self-registration until the workspace is claimed. That is exactly the kind of operational detail annotations cannot express.

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 sentences, front-loaded with what is read, then how to switch modes, then safety, then auth preconditions. No filler or restatement of the tool name.

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 two-optional-param read tool with no output schema, it covers the returned metrics, the history mode, range semantics, and both auth gates. An agent has everything needed to call it correctly or diagnose a 403.

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 coverage is 100%, so the baseline is 3; the description earns extra by explaining the dependency the schema leaves implicit — that duration_minutes only matters when history is true — and restating the 1–1440 bounds and default in context.

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 ('Read the AITune sidecar's current GPU and CPU load') and enumerates the returned signals (utilisation, memory, temperature). This is clearly separable from nearby siblings such as get_aitune_profiling and list_aitune_backends.

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?

Explicitly tells the agent to pass history=true to switch from current readings to a time-series, with the range and default spelled out. It gives prerequisites (credential, claimed workspace) but does not name a sibling alternative or state when not to use it.

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