Moovtips — digital agency

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

With no annotations, the description carries the full burden and does disclose real behavior: data is transmitted to a third party (Moovtips), an explicit consent gate is required, and a response arrives within 48 hours. It stops short of describing failure handling or what happens if consent is refused, but the third-party transfer and consent requirement are exactly the non-obvious traits an agent needs.

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 sentences with no padding: the action leads, the data-collection prerequisites follow, and the 48-hour SLA closes. Well front-loaded and every sentence carries information, though the middle sentence is dense.

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 12-parameter mutation tool with no annotations, no output schema and only 50% schema coverage, the description covers the consent flow and turnaround time but leaves the required 'services' enum unexplained and says nothing about the optional fields. Adequate but incomplete given the tool's complexity.

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 50%. The description names six of the eight required fields (prénom, entreprise, email, métier, ville, besoin) and reinforces the consent semantics with 'sans rien inventer', but it omits the required 'services' enum parameter and all optionals (delai, budget, langue, telephone), so it only partly compensates for the coverage gap.

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 (envoie) and resource (demande de devis) plus the recipient (Moovtips) and on whose behalf (au nom de la personne). The purpose is unambiguous, though it never contrasts itself with the siblings (services_moovtips, offres_par_metier, lien_questionnaire), so an agent must infer the boundary itself.

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 explicit pre-invocation steps: collect prénom, entreprise, email, métier, ville and besoin without inventing anything, then obtain explicit consent before sending. That is strong when-to-use context, but it names no alternatives or when-not-to-use conditions relative to the sibling tools.

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?

readOnlyHint=true already establishes the safety profile, so the lower bar applies. The description adds genuinely non-obvious behavior: the returned link embeds the pre-checked services, and the intended consumer is a third party who fills it in. No output schema exists, so the note that the result is a transmissible link is the key disclosure; expiry, format and auth needs remain unstated.

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 that opens with the verb and resource and wastes no words. The trailing conditional clause is informative rather than filler, though the sentence carries a lot at once.

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 two-parameter, read-only link generator with no output schema, the description covers what the tool does, what the link contains, and who should receive it — enough to call it correctly. The gaps are secondary: nothing about the language parameter or link validity.

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 only 50%: "services" is documented in the schema, while "langue" has an enum and a default of "fr" but no prose anywhere. The phrase "avec les services déjà cochés" maps implicitly to the services parameter, but the description never mentions the language parameter or how the two interact.

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 pair ("Donne le lien du questionnaire de projet Moovtips") and clarifies what the link contains ("avec les services déjà cochés"). The closing clause about transmitting it to someone implies the boundary with the sibling envoyer_demande (send the request vs. give a self-service link), but the sibling is never named explicitly.

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 a clear usage condition — use this when the person prefers to fill the questionnaire out themselves rather than having the agent submit on their behalf. It does not name envoyer_demande as the alternative or state any exclusions, 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.

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

readOnlyHint=true already establishes the safe read profile, so the description's job is to add context — and it does by disclosing the shape of the result: grouped offers per vertical, included services, and a quote link. It does not mention language behavior or rate/scope limits, but that is a minor gap against annotation coverage.

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 that wastes nothing; the resource and the returned content are both stated immediately.

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 usefully enumerates the returned content (offers, included services, quote link), which is the right move. However, for a tool with a language parameter it omits any mention of language/output localization, leaving that dimension undocumented.

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?

There is one parameter (langue, enum fr/en, default fr) with 0% schema description coverage, so the description carries the full burden — yet it never mentions language, localization, or which language output is returned. A user relying only on the description would not know the tool is localizable at all.

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 (Liste) and resource (offres groupées de Moovtips par métier), and enumerates the covered verticals plus the fields returned (services inclus, lien de devis). It does not distinguish itself from the closely related sibling services_moovtips, which likely also enumerates offerings.

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?

No when-to-use, when-not-to-use, or alternative-tool guidance is given. The overlap with services_moovtips (and lien_questionnaire for the quote link) is left entirely for the agent to infer.

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?

readOnlyHint=true already tells the agent this is a safe read, so the bar is lower. The description still adds real value by disclosing the return payload ('la page de chaque service et le lien de devis'), which matters because there is no output schema to document 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 usage instruction is nicely front-loaded at the end, but the service list is padded with a duplicated run ('flyers / cartes de visite / magnets' repeated after already listing 'flyers, cartes de visite et magnets'). That redundancy costs space without adding 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?

For a simple, read-only, one-optional-parameter listing tool, the description covers purpose, trigger, and return content. Nothing an agent needs to invoke it correctly is missing, though a note on the default 'fr' language would have closed the loop.

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 'langue' parameter carries its own enum and explanation ('Langue de la personne'), so the schema does the work. The description says nothing about language selection, leaving it at the baseline for a fully documented 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 ('Liste les services de l'agence digitale Moovtips') and enumerates the concrete offerings, so an agent knows exactly what comes back. It does not, however, differentiate itself from the sibling 'offres_par_metier', which an agent could reasonably confuse with a service listing.

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?

It gives an explicit trigger: 'Utilise-le quand une personne cherche l'un de ces services.' That is a clear when-to-use condition. There is no when-not guidance and no mention of the sibling tools that cover adjacent needs (demande, questionnaire, offres par métier).

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