Lampions — scrutins publics français

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

With no annotations, the description carries the full burden of behavioral disclosure. It conveys substantive traits: sort order (most recent to oldest), filterability by chamber and theme, and exclusion of amendment votes. It does not describe pagination, response format, or error conditions, but for a read-only list operation these are less critical.

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 compact sentences. The first front-loads the main purpose, scope, and ordering; the second adds a valuable exclusion with no redundancy.

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 read-only list tool with three optional parameters and no output schema, the description covers what is returned, ordering, filtering, and exclusions. It could mention that lire_scrutin is the way to retrieve full details of a specific vote, but that is not essential to call this 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 description coverage is 100%, so all three parameters are already documented in the schema. The description adds only that filtering by chamber and theme is possible, which reinforces but does not extend the schema.

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 ('sccrutins majeurs les plus réccents'), defines what qualifies as major (vote sur un texte, motion de censure, déclaration), specifies ordering, and clearly excludes amendments, making it distinct from amendment-level listing tools. Though it does not name the sibling lire_scrutin, the listing vs. reading contrast is inherent.

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 implies use when recent major votes are needed and explicitly notes that amendments are excluded, which serves as a when-not signal. However, it does not name or contrast the sibling lire_scrutin, nor state when that alternative should be used instead.

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 transparency burden. It candidly enumerates what is returned (title, question, vote counts, outcome, source dataset, license) and adds a privacy guarantee ('Aucune donnée personnelle'). The verb 'Rend' signals a read-only operation, so the safety profile is adequately conveyed, though error behavior for invalid IDs is not discussed.

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 a single, well-structured sentence that leads with the core action and resource, then appends the input condition, a colon-introduced list of outputs, and a privacy note. Every clause contributes new information without repeating the schema.

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 one-parameter lookup with no output schema, the description provides the input source, an example, and a comprehensive list of returned fields, which is sufficient for an agent to call it correctly. The only missing element is behavior on unrecognized identifiers, which is a minor gap for such a simple tool.

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 documents the `uid` parameter, including its nature and where identifiers are published. The description adds a concrete example (VTANR5L17V8430), but since schema coverage is 100%, this is a minor extra rather than a necessary compensation.

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 ('Rend le décompte officiel') and identifies the exact resource, a parliamentary vote from three chambers, plus the single required input (official identifier). The listed output fields and the 'à partir de son identifiant officiel' wording make this look-up tool implicitly distinct from the sibling listing tool 'derniers_scrutins'.

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 usage is implied: an agent should call this when it has an official vote identifier, as stated in 'à partir de son identifiant officiel'. There is no explicit mention of when not to use it or any comparison with 'derniers_scrutins', so the routing logic between the two tools is left to inference.

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