get_recipe

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

With no annotations, the description does real work by declaring 'Documentation only; never touches a device' and by explaining that values are raw register values with negatives as 16-bit two's complement — both genuinely useful behavioral facts. It stops short of stating what happens when the task string matches nothing (fuzzy match? error?) or whether lookups are case-sensitive, which matters given the free-text parameter.

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?

It is a single dense sentence fragment with no leading verb, front-loaded with the returned structure rather than the action. Every clause is informative — nothing is padding — but the list-of-fields format is harder to scan than a short lead sentence followed by 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?

With one parameter and no output schema, the description must stand in for the return shape, and it does so thoroughly: preconditions, steps with op/address/function code/value/check, confirmation reads, failure/recovery, notes, and provenance. Only the free-text matching behavior of the task parameter is left unexplained.

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% and the schema already gives both examples ('native.ems_session_start' and 'forced charge sunspec'), so the description adds nothing parameter-specific. Baseline 3 applies since the schema carries the semantics.

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?

The description enumerates what a recipe contains (preconditions, ordered steps, confirmation reads, failure/recovery, doc sections), so an agent knows exactly what resource it gets back, and the closing clause clarifies it is documentation, not device interaction. It never states a verb or explicitly contrasts with list_recipes, so the read-vs-browse distinction must be inferred from the name 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?

Usage is only implied: the schema shows it accepts an id or a natural-language task description, which suggests 'look up the procedure you need.' There is no explicit when-to-use guidance, no mention of list_recipes for browsing, and no pointer to validate_write or get_register for the follow-up actions the recipe describes.

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