Fondatoria

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond that by enumerating what the response covers (trial terms, free tier, Pack pricing TTC, inclusions, supported sites) — effectively substituting for the missing output schema. It does not state whether the pricing is authoritative or could go stale, which keeps it below 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?

Content is front-loaded with the offering and the parenthetical audience qualifier is compact, and the trailing sentence states the use case. The content enumeration is dense but each item earns its place by telling the agent what the answer contains; a slightly tighter phrasing would reach 5.

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 input schema, no output schema and only safety annotations, the description carries the burden of explaining what comes back, and it does so by listing the offering components and pricing-inclusive-of-tax detail. Nothing critical is missing for an agent to call it correctly; only freshness/authority of the pricing data is left unstated.

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 there is nothing to disambiguate; baseline for a no-param tool is 4. The description correctly implies a parameterless, fetch-everything call with no filtering options.

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 a concrete subject matter (Fondatoria's offering: 30-day trial without card, free site, Pack complet with TTC prices, what it includes, supported site types) rather than restating the title. An agent can tell this is a static information/FAQ-style tool about pricing, distinct from the 'preparer_*' siblings which imply action. It stops short of explicitly contrasting itself with those siblings by name.

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?

"Pour une question de prix ou de contenu de l'offre" gives an explicit trigger condition for calling it, which is exactly the selection signal an agent needs. It does not name alternatives or state when NOT to use it, so it falls short of a 5.

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 the safety profile (non-read-only, non-destructive, non-idempotent, closed-world), and the description adds substantial context beyond them: what Fondatoria does to the page (hosting, form, legal notices, SEO), that the owner can later edit without code, that the call returns the link where the owner verifies details and creates the site, and that invented reviews/figures/labels are held back until confirmed. That is exactly the kind of side-effect and outcome disclosure annotations cannot carry.

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 opening sentence front-loads the purpose and the rest are dense with operational detail; little is wasted. The first sentence is long and packs several clauses, but each carries information an agent needs.

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 takes on the job of explaining the return value (the link to the owner's site) and the confirmation flow, plus input format constraints and the treatment of unverified claims. Nothing needed to call this correctly appears to be 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?

Schema coverage is 100%, so the baseline is 3; the description still adds meaning by clarifying what the html payload may contain (Tailwind via CDN, Google fonts, scripts, styles, images as links) and by framing nom/email/telephone/ville as the owner's real coordinates that get verified. The allowed-resource detail is genuinely absent from 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 names a specific verb and resource: it puts online the showcase site the agent just wrote in HTML, and lists the concrete transformations (hosting, contact form, legal notices, SEO, no-code editing). This is far from tautological. It does not, however, distinguish itself explicitly from the sibling tools (preparer_creation, preparer_refonte), so it stops short of a 5.

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?

'Le site vitrine que vous venez d'écrire' and 'Envoyez la page complète telle que vous l'avez écrite' establish that this runs after the HTML page exists and that the exact written page should be submitted. Usage context is clear, but no explicit exclusions or named alternatives are given, so it is a 4 rather than a 5.

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, closed-world), and the description adds real context beyond them: the call returns a link, the assistant then proposes style/colors/texts, and the site builds live in front of the client. That end-to-end workflow is genuinely useful and consistent with readOnlyHint=true since nothing is persisted here.

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, front-loaded with the action and the return value. The closing clause « le site se construit sous les yeux du client » is slightly promotional but still conveys that the assistant takes over after the call, so it earns most of its space.

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 correctly compensates by explaining what is returned (a link) and what happens next. For a two-parameter preparation tool with full annotation coverage, the remaining gap is minor — no mention of failure cases or what happens if the description is rejected by the length bounds.

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 both parameters are already documented, including the notable « Ignoré » semantics of the formule enum. The description only reinforces that the activity description arrives pre-written; it adds nothing about the formule quirk or the 20–2000 character bounds, so the schema is doing the heavy lifting.

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 (prépare la création d'un site vitrine) plus the concrete return value (le lien vers l'assistant de création). The qualifier « pour une entreprise qui n'en a pas encore » implicitly distinguishes it from the sibling preparer_refonte, so an agent can route between the two without opening the 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?

The condition for use is stated clearly: a business that does not yet have a site. That doubles as an exclusion (an existing site points to refonte) and the post-call flow is described. However, no sibling is named explicitly, so the routing is inferred rather than spelled out.

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 and closed-world, so the safety profile is covered. The description adds value beyond them: the call is free, it returns a link, and the preview is generated from the owner's own content in a few minutes. It does not mention any auth or rate-limit constraints, keeping it below a 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 action, then the returned artefact, then the qualifying audience; no filler. The closing audience sentence is somewhat promotional but earns its place by carrying the when-to-use signal.

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?

There is no output schema, and the description compensates by explaining the return value (le lien où le propriétaire lance l'aperçu). Combined with 100% schema coverage, an agent has what it needs to invoke it correctly; only edge behaviour (preview expiry, re-invocation effects) is left implicit.

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 both params (url, formule) are documented in the schema itself, including the unusual note that formule is ignored. The description adds nothing about parameter formats, so 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?

States a specific verb+resource (prépare la refonte d'un site vitrine) plus its input (l'adresse du site actuel) and its output (le lien de lancement de l'aperçu). 'À partir de son adresse' implicitly separates it from a from-scratch creation tool, but no sibling is named, so differentiation is inferred rather than 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?

Gives clear qualifying context: an artisan/commerçant/petite entreprise whose site is daté, lent, mal adapté au téléphone or trop cher chez Wix. It never says when NOT to use it or names decrire_offres / preparer_creation as the alternative, so it stops short of full routing guidance.

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