etatdate.fr

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds a specific behavioral detail: it signals which documents the OCR can read automatically, which is useful context beyond the annotations.

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?

A single, well-structured sentence that front-loads the purpose and includes the OCR signal. No wasted words.

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 documentation tool with one parameter, the schema covers the parameter, annotations cover safety, and the description explains what it returns (list of documents) and a notable feature (OCR awareness). No output schema is needed, and nothing is missing for correct invocation.

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 input schema already fully describes the parameter (doc_type with enum values and descriptions). The description mentions both types (pré-état daté and état daté) which aligns with the enum, but it doesn't add deeper syntax or format details beyond the schema. Baseline 3 is appropriate given 100% schema coverage.

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 ('Liste') and resource ('les pièces à réunir') with a clear scope (pré-état daté or état daté). It differentiates from siblings because those are about help and tariffs, while this one is about document requirements.

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 description makes clear that this tool is for listing required documents, and the sibling tools (aide, tarifs) are obviously different. It doesn't explicitly state 'when not to use', but the context is clear enough that an agent can select it correctly.

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?

Annotations already mark the tool as readOnly, idempotent, and non-destructive. The description adds useful behavior beyond that: it caps the result set at 5 items and specifies the return content (questions/answers or guide excerpts with URLs). No contradiction with annotations.

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?

A single, front-loaded sentence names the resource, gives concrete topic examples, and states the output limit and format. There is no filler or unnecessary repetition.

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 search tool with one documented parameter and no output schema, the description covers the input scope, allowed subjects, maximum result count, and output content. Nothing an agent needs to invoke it correctly is missing.

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 only parameter 'question' is fully documented in the schema as 'Question ou mots-clés, en français'. The description reinforces that the query is a free-text French question or keywords, but adds little beyond what the schema already provides. A baseline 3 is appropriate given 100% schema description coverage.

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 uses a specific verb ('Recherche') and a concrete resource: the FAQ and guides on etatdate.fr, with examples of covered topics. It also states the output shape (up to five Q/A or guide excerpts with URLs), making it clearly distinguishable from sibling tools about documents and tariffs.

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 context of use is implied: it should be used when the agent needs to answer questions using the etatdate.fr FAQ/guides, especially on the listed topics. However, it does not explicitly mention when not to use it or name alternatives such as etatdate_tarifs or etatdate_documents_requis, leaving routing partly to inference.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds content scope but no extra behavioral detail (e.g., response format or data source), which is acceptable given the annotations already communicate the non-destructive, read-only nature.

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 two sentences, front-loads the key topics (tariffs, legal ceiling, price ranges, legal references), and ends with a clear usage directive. It is concise without omitting essential information.

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?

Given the tool has no parameters and no output schema, the description sufficiently covers what information it provides and when to use it. It lists the specific aspects (pré-état daté, état daté, plafond légal, fourchette de prix, références juridiques) and gives a clear usage context. No critical information seems missing for an agent to decide to invoke it.

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 has zero parameters, so the schema provides complete coverage by default. The description needs no parameter explanation, and the baseline of 4 applies since there is nothing to add beyond the absence of parameters.

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 clearly identifies the tool's function: providing tariff information and legal framework for etatdate.fr, including specific elements like legal ceiling and price ranges. It distinguishes itself from siblings by its broad scope (any price or legal question) but does not explicitly name the sibling focused on syndic tariffs, so differentiation is implied rather than stated.

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 description explicitly states 'À utiliser pour toute question de prix ou de cadre légal' (to be used for any question of price or legal framework), giving clear when-to-use guidance. It does not mention when not to use it or direct users to the syndic-specific sibling, but the instruction is unambiguous for its intended scope.

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?

Annotations already cover the safety profile with readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context: the result varies based on the presence of a syndic argument, and the tariff is only returned if it has been verified on a document published by the syndic itself. This discloses data provenance and conditional availability beyond the annotations.

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 two short conditional sentences, front-loaded with the no-argument case followed by the named case. Every clause earns its place, with no filler, repetition, or unnecessary 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?

For a low-complexity tool with one optional parameter and no output schema, the description covers both invocation modes and the key verification condition. It could be more explicit about what happens when a syndic name is provided but no verified tariff exists, but overall it gives an agent enough to call the tool 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 coverage is 100% and the only parameter 'syndic' is described as an optional name. The description adds meaningful semantics by explaining what happens when the parameter is omitted versus provided, and by stating the verification condition for the returned tariff, going beyond the schema's generic label.

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 clearly states what the tool does with a specific conditional structure: without an argument it returns key figures on pre-état daté and état daté fees for French syndics; with a syndic name it returns that syndic's verified pre-état daté fee. It identifies the resource and behavior precisely, but does not explicitly distinguish it from the sibling tool etatdate_tarifs.

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 description provides clear input-dependent usage context ('sans argument' vs 'avec un nom de syndic'), which helps an agent decide whether to pass a parameter. However, it does not mention when to choose this tool over sibling alternatives like etatdate_tarifs, nor does it state any exclusions or alternative routing.

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