DIKOO

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 goes further by disclosing the scope of what the response explains AND what it deliberately does not cover ('pas de conseil juridique, pas de vente de contacts'), which is meaningful behavioral framing for an informational tool with no output schema.

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?

Both paragraphs are dense and front-loaded with the core claim ('gratuit pour lui'), with no filler. The bilingual duplication roughly doubles the length, but it serves a French/English audience and each sentence carries distinct content.

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 zero-parameter, annotation-covered, output-schema-less informational tool, the description adequately previews the content the agent will get back, including its limits. Only the explicit usage trigger and any return-format expectation are 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 per the rubric this hits the baseline of 4. Nothing in the description conflicts with the empty 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 informational purpose and enumerates the exact topics covered (free for the user, verified lawyers, video/in-person appointments, data protection, and explicit non-goals). It reads as clearly distinct from the sibling action tools like rechercher_avocats or verifier_avocat, though it never names a sibling to contrast with.

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 this is the tool for questions about DIKOO itself, and 'pour un particulier' scopes the audience. There is no explicit when-to-use statement, no exclusions, and no routing to/away from siblings.

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, closed-world and non-destructive, so the safety profile is covered. The description adds real value beyond them: it discloses the return content (each slot carries its modes and a dikoo.fr booking link) and the 14-day hard cap. It does not mention result-size limits or pagination, which is the only remaining gap.

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?

Each language version is tight and front-loads the scoping constraint and the alternative. The cost is that the entire text is duplicated in French and English, roughly doubling the token footprint for an agent that only needs one language, but no sentence is filler within a given language.

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 what each returned slot contains (modes, booking link) and the maximum query window. Combined with the explicit alternative-tool routing, an agent has everything needed to call this 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 the schema already documents avocat, du, au and the visio/cabinet enum. The description restates the 14-day cap and the modes but adds no format or syntax detail beyond what the schema provides, so the 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: bookable consultation slots for a DIKOO-registered lawyer, over a bounded period, with the per-slot payload (modes, booking link) spelled out. It explicitly distinguishes itself from the sibling lien_rendez_vous by naming the registered vs directory-only lawyer condition.

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 an explicit routing rule with the selecting condition: use this for a registered lawyer, use lien_rendez_vous for a directory-only lawyer. The 14-day maximum window is also stated as a hard usage constraint, so an agent knows the valid call envelope before invoking.

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?

Read-only, idempotent, non-destructive behavior is declared in annotations, so the description needn't restate it. It does add valuable disclosure beyond annotations: the privacy guarantee ('Jamais d'email ni de téléphone' / 'Never email or phone') and that fees are only shown for registered lawyers, which tells the agent what data will be absent. It could go further on error behavior for an unknown id, but the explicit privacy constraint is meaningful.

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?

Dense but zero-waste: each clause enumerates a returned field or a constraint. The bilingual duplication and the legal disclaimer are front-loaded and purposeful. No filler sentences.

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 1-param read-only lookup with full schema coverage and no output schema, the description covers what the tool does, what it returns, and the key data-privacy boundary. It is nearly complete; only error/unknown-id behavior and pagination are unaddressed, which are minor for this tool shape.

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 parameter's description already explains 'Public id or dikoo.fr profile URL'. The description repeats this ('à partir de son identifiant ou de l'URL de sa fiche dikoo.fr') but adds no format details, no exclusions, no examples. Baseline 3 for full schema coverage.

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?

Names a specific resource (fiche publique d'un avocat) and specifies the lookup key (identifier or dikoo.fr URL). It enumerates the returned fields, which sharply distinguishes it from siblings like rechercher_avocats and creneaux_disponibles.

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 it is for fetching one profile by id or URL, and the enumeration of fields implies 'use when you already have an id', but it never states when NOT to use it or points to alternatives (e.g. rechercher_avocats for discovery, verifier_avocat for verification). Usage is inferable but not explicit.

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 and non-destructive, so safety is covered. The description adds genuinely new behavioral context: no personal data in the URL, the user verifies via SMS+email, and the agent must not book on the user's behalf — a real constraint not expressible in annotations. It does not describe URL lifetime/expiry or what happens if an invalid slot id is passed.

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 action and is given bilingually, which doubles length but each version is tight. The French and English passages are largely duplicative, a minor cost, but no sentence is wasted.

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 URL-builder with a fully documented 4-param schema and no output schema, the description covers the action, the two URL outcomes, the privacy property, and the agent's responsibility. Nothing needed to call it correctly is 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 every parameter including mode's enum is already documented in the schema. The description adds the conceptual distinction between registered and directory lawyers but no per-parameter syntax beyond schema, 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 and resource (génère l'URL dikoo.fr) and precisely distinguishes two booking flows (registered lawyer vs. directory lawyer), which no sibling tool does — creneaux_disponibles returns slots, this one builds the booking URL.

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?

Explicitly says to always hand the link to the user and never book on their behalf, and the mention of mode/slot context implies this follows creneaux_disponibles or rechercher_avocats. When-to-use and when-not-to-act are both 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 declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavioral context: it is advisory-only (no legal advice), takes a short anonymized description, and returns named practice areas plus an explanation and a search link. Given annotations, this is solid additional context.

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?

Bilingual, front-loaded with what the tool returns, then the scope limitation in a single tight clause. Every sentence earns its place; 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?

No output schema exists, yet the description names the three returned elements (practice areas, a 2-3 sentence explanation, a dikoo.fr search link), which is exactly what the agent needs. It covers scope, input constraints and output shape. Slightly less complete on routing logic versus siblings, but strong overall.

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 the schema already fully documents the single 'besoin' parameter including length bounds and the no-personal-data constraint. The description repeats the same no-personal-data caveat, adding little beyond the schema. Baseline 3 is appropriate.

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 ('indique les spécialités d'avocat pertinentes') from a short problem description, and explicitly delimits what it is not ('l'outil nomme des spécialités, il ne répond pas sur le fond'). Distinguishable from siblings like rechercher_avocats, which implies a search over a directory rather than a routing/classification of a need.

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?

Clear context is given: short description, no personal data. The 'Aucun conseil juridique' framing tells the agent what this tool is not for. However, no explicit when-to-use-vs-alternatives guidance (e.g. vs rechercher_avocats for an already-known specialty) is provided.

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/openWorld=false, so safety is covered. The description adds genuinely useful behavior beyond that: pagination caps (10 per page, 5 pages max), result ordering (DIKOO-registered with open calendars first, then national directory), and the fallback 'disponiblesEnVisio' list.

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-loaded and logically ordered, but the entire content is duplicated verbatim in French and English, doubling the token footprint with no added information for the agent. The redundancy means not every sentence 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?

With no output schema, the description compensates well by naming the key result fields ('url', 'lienRendezVous'), the pagination behavior, the fallback result list, and the legal-advice disclaimer. It stops short of explaining how optional filters combine or result ordering precedence beyond the DIKOO-first rule.

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 seven parameters (including the lieu/ville alias) are already documented, and the description merely restates the filter dimensions (city/postal code, practice area, mode, language, availability). No additional syntax or combination rules are added, so the 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 and resource ('Recherche d'avocats en France') plus the filter dimensions and scope (public paginated profiles). It is clearly distinct from siblings like fiche_avocat or verifier_avocat in intent, though it never names a sibling to disambiguate against.

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 one concrete usage rule — when a location has no bookable lawyer, the response surfaces 'disponiblesEnVisio' nationwide results — which is actionable. However, it never states when to prefer this over fiche_avocat, verifier_avocat, orienter_besoin or creneaux_disponibles, so routing between siblings 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.

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds meaningful behavior beyond that: the authoritative data source, that the answer is a registration check, and that a profile link is returned. It does not discuss ambiguity handling (e.g. homonyms, empty results), which keeps it from 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-loaded with the core action and scoped constraints in one compact sentence per language. The French/English duplication doubles the length in the raw string but is deliberate bilingual support rather than padding; there is no wasted clause.

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 carries the return-value burden by stating both result facets (directory presence and DIKOO registration) plus the profile link. Combined with annotations covering the safety profile, an agent has everything needed to call this 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 the schema already documents all four parameters including the 'prenom recommended' hint. The description restates the selectable criteria ('nom, prénom, ville ou barreau') and their disjunctive nature but adds no new syntax, matching or precedence rules, so the 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 states a specific verb and resource: verify whether a lawyer (by last name, first name, city or bar) appears in the national directory and is registered on DIKOO, returning the profile link. It also names the data provenance (CNB data aggregated by DIKOO), which sharpens the scope. It never explicitly contrasts itself with the close sibling rechercher_avocats, 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?

There is no explicit when-to-use guidance and no mention of the alternative (rechercher_avocats for discovery, fiche_avocat for details). An agent can infer this is an existence/eligibility check rather than a search, but the description leaves the routing decision entirely to inference.

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