Info Scolarité

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: the fiche is read by official UAI code and 'chaque donnée est accompagnée de sa source et de son année', which tells the agent about data provenance and freshness.

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?

Three tight sentences, purpose front-loaded, followed by input sourcing and a data-provenance note. No padding; each sentence carries information, though the final sentence is a minor add-on.

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 single-parameter read tool with rich annotations and no output schema, the description covers both the input (how to obtain the UAI) and the output shape (the field groups returned). Nothing essential is missing, though error behavior for an unknown UAI is unaddressed.

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 pattern is documented, so baseline is 3. The description goes beyond the schema by explaining where the UAI comes from (the search tool's results) and giving a concrete example (0350760L), which helps an agent obtain a valid value.

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 ('Présente la fiche') and resource ('établissement'), then enumerates exactly what the record contains (identité, coordonnées, dispositifs, effectifs, résultats, IPS, lettre de notation). This clearly distinguishes it from trouver_etablissement (search) and secteur_d_une_adresse (address lookup).

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 implied rather than stated: by noting the UAI is 'le code officiel que l'outil de recherche donne pour chaque résultat', it hints the tool follows a search. However, no sibling is named, and there is no explicit when-to-use/when-not guidance for choosing between it and trouver_etablissement.

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 establish read-only, idempotent, open-world behavior. Beyond that, the description adds meaningful context: the result applies to this address only, only published school-map territories are covered, the address queries the Base adresse nationale, and the site does not retain it.

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 front-loaded with the main purpose and then adds useful scoping, output, coverage, authority-confirmation, and privacy details. It is somewhat dense but every sentence contributes relevant context.

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 single-parameter, open-world lookup with no output schema, the description is complete enough: it explains what is returned, the address-level scope, coverage limits, confirmation authority, and address handling. An agent has enough information to call it 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?

The single parameter has 100% schema description coverage, including the format (number, street, city or postal code) and the address-specific scope. The description adds the BAN query and non-retention context, but the core parameter semantics are already supplied by 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 uses a specific verb and resource: 'Trouve le collège public de secteur d'une adresse'. It clearly distinguishes an address-level sector lookup from a commune-level lookup, but it does not explicitly differentiate itself from the sibling tools lire_fiche and trouver_etablissement.

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 implied by the stated scope and by the caveat that only territories with a published school map are covered. However, the description does not explicitly say when to use this tool versus the sibling tools trouver_etablissement or lire_fiche.

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 readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real value beyond that by stating what the response contains (UAI, notation letter when it exists, link to the fiche) and the ordering rule (by match relevance). It does not discuss rate limits or pagination, so a 4 rather than 5.

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?

Front-loads the core purpose and keeps each sentence doing work (purpose, examples, filters, return content, ordering, alternative tool). Slightly long and the response-content sentence could be tighter, but there is 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?

With no output schema, the description compensates by describing the returned fields and ordering. Combined with the explicit alternative-tool routing and filter enumeration, an agent has everything needed to invoke this search 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%, so the baseline is 3, but the description earns extra by giving concrete syntax examples ('collège Rennes', 'lycée professionnel Lyon') that show how to combine name and commune in the required 'recherche' field, plus naming the secteur and dispositif filters.

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 (cherche) plus the exact resource set (écoles, collèges, lycées) and the search dimensions (nom, commune, niveau). It also names the sibling tool to use for a related but different need, letting an agent distinguish it without opening another schema.

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?

Provides concrete query examples, lists the optional filters, and explicitly routes an alternative case (collèges around a location with distance) to the secteur tool with the required street number. This is clear when-to-use and when-to-use-something-else guidance.

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