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

With no annotations at all, the description carries the full burden and does disclose the safety profile ('Lecture seule') plus the range and end-date limits, which are real behavioral boundaries. It omits what happens on invalid or future dates and whether days without data appear as gaps or zeros.

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: purpose and return values first, then format, then limits, then read-only status. Every sentence adds a fact an agent needs, with no filler.

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-parameter read tool with no output schema, the description covers return shape (daily values, total, average), input format and validity limits. The remaining gap is edge-case behavior — missing data days and error responses — but nothing essential to issuing a correct call is absent.

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 0% — the properties are bare strings titled 'Debut' and 'Fin' — so the description must compensate, and it does: date format AAAA-MM-JJ with an example, inclusive boundary semantics, and both range limits. Only the interplay of debut/fin validation errors is left unstated.

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: daily electricity consumption in kWh between two inclusive dates, plus total and average. That clearly distinguishes it from conso_veille (single day), courbe_charge (load curve) and puissance_max (peak power), though no sibling is named 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?

Gives concrete applicability windows: maximum 366 days per call and an end date no later than yesterday. These constraints tell an agent when the call is valid, but no alternative tool is named for out-of-range cases or for single-day queries.

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

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

With no annotations, the description carries the full burden: it correctly discloses read-only behavior ('Lecture seule') and the return unit, which is valuable. It says nothing about what happens when yesterday's data is missing or delayed, which matters for an energy-metering tool.

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?

Two short sentences, front-loaded with what is returned, followed by the usage cue and the read-only note. No filler.

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 no-param, no-output-schema tool this covers what it returns, the unit, and the trigger. The only gap is how 'hier' is resolved (timezone / data availability window).

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?

The tool takes zero parameters, so the baseline is 4; the description makes clear no user input is needed. There is nothing further to add.

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 the household's electricity consumption, with unit (kWh) and time window (yesterday), which distinguishes it implicitly from conso_periode. It stops short of naming the sibling it differs from, so it's clear but not fully differentiated.

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?

The quoted user utterance 'combien j'ai consommé hier ?' gives a concrete trigger, and 'hier' implicitly routes away from conso_periode. However, no alternative tool is named and no when-not condition is given.

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

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.

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

With no annotations, the description still discloses key behavior: it is read-only, defaults to yesterday when no dates are supplied, and dates are inclusive. It does not cover permissions, error behavior, or edge cases such as supplying only one date.

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 compact and front-loaded: purpose first, then practical usage, default behavior, date format, and read-only status. Every sentence adds useful information with no filler.

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 read-only query with no output schema and no annotations, the description covers purpose, use case, default period, date format, inclusivity, and read-only safety. Remaining gaps are minor edge cases around partial date ranges and timezone assumptions.

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 0%, so the description must carry parameter semantics. It usefully adds the date format AAAA-MM-JJ, the fact that dates are inclusive, and the default of yesterday, but it does not clarify individual behavior for debut versus fin or partial parameter combinations.

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 gives a specific verb and resource: it returns daily maximum reached power in VA and the strongest day in the period. This is clear enough to identify the tool, though it does not explicitly distinguish itself from siblings such as conso_periode or courbe_charge.

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 provides a clear use case: determining whether the subscription is too small or too large, and states the default behavior when dates are omitted. It does not explicitly say when to prefer this over sibling tools like conso_periode or courbe_charge.

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