Registers

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds a genuine behavioral caveat beyond that: only the FIRST address matching the supplied label is profiled, which affects how an agent should interpret results. It says nothing about lookup failures or result ambiguity beyond that.

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 sentences, both dense with information and no filler; the contents list is front-loaded and the matching caveat trails it appropriately. Slightly list-heavy but every item earns its place.

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?

An output schema exists, so return-shape explanation is unnecessary, and annotations carry the safety and world-access profile. For a single-parameter read tool, the description plus those structured fields give the agent everything needed to invoke 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?

Schema description coverage is 0% for the single 'address' parameter, so the description must compensate. It clarifies that the input is a free-text 'libellé' and that only the first match is used, which is real added meaning, but gives no format or syntax guidance (e.g. street-number/city format) and no hint about what happens when nothing matches.

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 concrete verb-resource pair (return the public profile of an address) and then enumerates exactly what the profile contains: commune, nearby parcels, risks, RNB buildings, PLU zoning, RNIC, DPE. That enumeration effectively distinguishes it from get_parcel_profile, though the sibling is never named.

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 never says when to use this tool versus get_parcel_profile or search_places, and gives no prerequisites. Usage is only implied by the word 'adresse' and the enumerated contents, so the agent must infer routing from sibling names alone.

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 read-only, idempotent, open-world, and non-destructive behavior. The description adds that the fiche is public and lists the data sections included, but it does not disclose error/not-found behavior, rate limits, or whether some sections may be absent beyond the phrase 'chiffres clés disponibles'.

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, front-loaded sentence that lists the relevant data categories without filler. Every element contributes to the agent's understanding of what the fiche contains.

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 an output schema, rich annotations, and a fully documented single parameter, the description is largely complete for calling the tool. Minor gaps remain: it does not mention sibling search alternatives and says 'par SIREN' while the schema also accepts SIRET.

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%, and the schema already documents that the parameter accepts a 9-digit SIREN or 14-digit SIRET with a pattern. The description adds little beyond the schema and is actually narrower by mentioning only SIREN, so the baseline of 3 applies.

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 resource ('fiche publique d’une entreprise') and the lookup key ('par SIREN'), and enumerates the categories of data returned. It is easy to distinguish from search-oriented siblings in practice, though it never explicitly contrasts itself with search_companies.

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: this is a direct lookup by SIREN versus the sibling search tools. However, the description does not explicitly say when to use this tool instead of search_companies, nor does it state prerequisites or exclusions.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: the data domains returned and an explicit data exclusion (no owner information), which is the kind of boundary an agent cannot get from structured fields. It does not discuss not-found handling or the fact that data is aggregated from multiple external registries, which the openWorldHint implies.

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?

One sentence front-loads the core purpose and enumerates the payload, followed by a short exclusion clause. Nothing is wasted and there is no restating of the title or annotations.

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 an output schema present, return values need not be explained, and annotations cover the safety profile; the fully documented single required parameter leaves little gap. The only shortfall is that edge-case behavior (invalid or unknown parcel ID, empty registries) is unmentioned, which is minor for a read-only lookup.

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% and the single parameter parcel_id is documented in the schema with a 14-character format and a regex pattern. The description says nothing about the identifier format or accepted values, so it adds no meaning beyond the schema; baseline 3 applies.

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 names the specific resource (a public cadastral parcel profile) and enumerates exactly what it returns: location, risks, RNB buildings, five years of DVF sales, and attached RNIC co-ownerships. It also draws a firm boundary ('Ne fournit pas le propriétaire'). It is clear what the tool does, though it never names a sibling such as get_address_profile, so the routing between them relies on the word 'parcelle'.

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 only implied: an agent can infer it should call this when it has a cadastral parcel ID and needs the aggregated public profile. The negative statement 'Ne fournit pas le propriétaire' usefully signals a case this tool does not cover, but no alternative tool is named for that need and no explicit when-to-use condition is stated.

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 readOnly/idempotent/non-destructive/openWorld, so the description's added value is the establishment-level geography semantics and the required-criterion rule — both meaningful behavioral context. It does not disclose pagination ceilings (page max 20, per_page max 10) or ranking/sorting behavior, which would matter for a broad search.

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 sentences, front-loaded with the searchable keys, then constraint, then a semantic caveat, then return shape. Dense and largely waste-free, though the return-value sentence is partly redundant with the output 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?

Covers the essentials for an 8-param search tool: at least one criterion, geo-filter scope, and what comes back. Gaps are pagination limits and result ordering, which an agent would want when narrowing broad searches.

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?

With 50% schema coverage, the description usefully explains that q accepts name, SIREN, SIRET, or director name and that the listed filters are optional. It adds little for page/per_page (undocumented in the schema) beyond implying paging exists, and doesn't mention the maximums.

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 ("Recherche des entreprises françaises") and enumerates the searchable keys (nom, SIREN, SIRET, dirigeant), which clearly separates it from the single-record sibling get_company. It never names a sibling or explicitly contrasts with get_company/search_places, so it falls short of the top tier.

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?

"Au moins un critère est requis" supplies a real gating rule the schema does not express (required is empty). "Les filtres géographiques portent sur un établissement quelconque, pas seulement sur le siège" tells the agent how to interpret results before calling. No explicit alternatives or when-not guidance 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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the description only needs to add context. It does: it warns that multiple results are possible and that an address query also returns nearby parcels, which is real behavioral information not present in 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?

Three short sentences, front-loaded with the accepted input types, followed by the return-side caveats. 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 an output schema present, return values need not be detailed, and the description still adds the key caveats (multiple results, nearby parcels). Only minor gap is behavior on malformed or unmatched identifiers.

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 carries the burden and does so well: it explains that the single parameter accepts either a free-text address or a 14-character parcel identifier, and gives a concrete identifier example. It does not restate the 3–200 length bounds, but those are enforced 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?

States a specific verb and two concrete resources: French address lookup and cadastral parcel lookup by 14-character identifier, with an example. The search-vs-profile distinction against siblings get_address_profile/get_parcel_profile is implied but never made explicit.

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 two supported input modes are clear enough to imply when the tool applies, but there is no explicit routing guidance such as using get_parcel_profile once an identifier is known, and no statement of what it does not handle.

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