courbe_charge

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

With no annotations, the description carries the full burden and does well: it declares the tool is read-only ('Lecture seule'), states the prerequisite Enedis activation, and defines the default and maximum date range. It does not cover error behavior when recording is inactive, but the core behavioral constraints are disclosed.

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?

The description is short, front-loaded with the core output, and each sentence adds actionable information: format, default, limit, prerequisite, and read-only status. No waste.

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 simple two-optional-parameter tool with no output schema, the description explains what is returned (30-minute average power and energy), the date constraints, the default, and the activation prerequisite. It is nearly complete, though it could say more about partial date ranges or inactive-recording errors.

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 specifies the date format (AAAA-MM-JJ), that dates are inclusive, the default when omitted (yesterday), and the maximum span (7 days). It does not clarify behavior when only one of debut or fin is supplied, but the essential semantics are covered.

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 states a specific verb and resource: it returns consumption every 30 minutes, including average power in watts and energy in kWh. This clearly distinguishes the tool's high-frequency interval data from siblings like conso_periode, but it does not explicitly name or contrast those siblings.

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?

It gives clear usage context: no dates defaults to yesterday, the maximum range is 7 days, and it only works if the client has activated load-curve recording at Enedis. It does not explicitly name alternatives such as conso_periode or state when not to use this tool.

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