load_device_pack

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

Annotations only declare the write/repeat safety profile; the description adds substantive behavior: malformed packs are rejected with a problem list, never half-loaded, and shadowing a built-in family is gated behind allow_override=true. That is exactly the extra context the annotations do not carry.

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?

Purpose is front-loaded in the first clause, followed by coverage facts, input modes, and failure semantics in a tight block. Slightly dense and the 'Facts are DATA, never guessed' phrasing is rhetorical rather than operational, but every other sentence earns its place.

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?

With no output schema, the description covers return behavior (rejection with problem list, coverage report on no-arg call) and the override prerequisite. An agent has everything needed to invoke it correctly.

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 description's parameter remarks (path as JSON file, inline pack precedence, override gating) largely restate what the schema already documents. It adds no syntax or format detail for session, so baseline 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?

States a specific verb+resource ('Register a verified device-fact pack') and names the exact content it controls (DMA request routing, NVIC vectors, PLL profile, timer bus/width), which distinguishes it from sibling loaders like load_svd or describe_board. An agent can tell what this does without opening the 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?

Explains the trigger (adding a new STM32 family beyond the built-in F4/L4), the two input modes (path= JSON file or inline pack=), and a no-argument mode that reports current coverage. It lacks explicit when-not-to-use guidance or a named alternative, so it falls short of a 5.

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