Propecto

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

Beyond the readOnlyHint/openWorldHint annotations, it discloses API-key gating (territories/sectors work without a key, companies require one), a unit cost (2 for territory, 1 for company), and the output contract: every figure carries a [S1]/[S2] citation, missing values are reported as 'non disponible', and scheduling is described but not executed. These are exactly the behavioral traits annotations cannot convey.

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?

It front-loads the purpose and then groups details by the two invocation modes, with cost and constraints last. It is dense but every clause (return content per type, citation rule, API gating, cost) contributes information; only minor tightening of the long coastline-style sentence would improve it.

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, so the description must describe the return content — and it does so thoroughly: stock, monthly flux, baromètre, 1-5 year trends for territories, and last exercise plus sector/territory quartile positioning for companies, along with the citation legend. Combined with annotations, nothing essential for correct invocation 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?

With 100% schema coverage the baseline is 3, but the description goes further by supplying full JSON invocation examples ({"type":"territoire","niveau":"departement","code":"69"} and {"type":"societe","siren":"791143795"}) that show the cross-parameter relationship between type, niveau and code, plus the siren format, adding genuine value over the schema alone.

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: statistical analysis of a territory or company producing a written French synthesis. It clearly carves out a distinct capability (a cited, prose synthesis) rather than raw data lookup, which implicitly separates it from siblings like propecto_societe or propecto_finances, but it never explicitly names those siblings.

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 explicit branching guidance: use type="territoire" with niveau/code for aggregated territory or sector data, type="societe" with siren for company analysis. It states the exclusion clearly — company analysis is reserved for API keys — and specifies cost per call, so an agent knows exactly which invocation path to take and under what conditions.

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 mark this as read-only and closed-world. The description adds valuable behavioral details: only legal entities are listed, individual businesses are counted in personnes_physiques_non_affichees, the source is DECP, and the cost is one quota unit. This goes well beyond the annotations without contradicting them.

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 opens with the main purpose, then efficiently covers output fields, exclusions, source, and cost. It is somewhat dense, but each sentence adds useful information and there is no redundant 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 listing the returned buyer summary, principal supplier fields, and the handling of individual businesses. It could clarify what 'principaux' means or the sorting criteria, but overall an agent has enough to understand the response 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?

The schema already describes both parameters fully, including SIREN/SIRET format, tolerances, limits, and default. The description adds only an illustrative example and restates the input requirement. With 100% schema coverage, the baseline of 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?

The description clearly states the specific action: list companies that won contracts with a public buyer, using a SIREN/SIRET. It also summarizes the returned buyer info and principal suppliers. It does not explicitly distinguish itself from sibling tools like propecto_marches_remportes, but the buyer-centric scope is evident.

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 gives clear usage context: provide a public buyer's SIREN or SIRET to retrieve winning suppliers, with an example for Lyon. It does not explicitly mention exclusions or alternatives among siblings, but the input condition is explicit and unambiguous.

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?

Beyond the annotations (readOnlyHint=true, openWorldHint=false), the description discloses substantial behavior: results come from an offline Propecto cache with no third-party call, expired badges are never returned, ceased companies receive no badges, anonymous callers do not get sole proprietorships, and each badge carries an evidence level (verifie vs declare), source, verification link, and validity dates.

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 core return value and then packs in useful detail without filler. It is a single dense paragraph, so it could be more scannable, but every sentence contributes important 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?

With no output schema, the description fully explains what each badge object contains (code, libellé, catégorie, niveau de preuve, source, lien de vérification, since, valid_until). It also covers edge cases (expired badges, ceased companies, anonymous access) and quota cost, leaving no critical gap for correct invocation or interpretation.

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 accepted identifier formats (SIREN, SIRET, TVA FR, BCE), examples, whitespace tolerance, and checksum validation. The description repeats the identifier types and gives an example but adds no format or validation detail beyond what the schema provides.

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 opens with a specific verb and resource: 'Renvoie les badges EN COURS d'une société'. It then enumerates exactly which badge types are returned (certifications, labels, agréments, official registrations, marchés publics), making it clearly distinct from siblings like propecto_finances or propecto_marches_remportes.

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 context is clear: this is the tool for current certifications, labels, and official badges of a company. It also provides practical constraints (1 quota unit, anonymous access excludes sole proprietorships, expired badges are never returned) that help an agent decide when to call it. However, it does not explicitly name sibling alternatives or state when not to use it.

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 provide readOnlyHint=true, and the description adds substantial behavioral context beyond that: the ordered result set, null meaning 'donnée non publiée', the anonymous-access limitation for individual enterprises, and quota cost. It also discloses the exact fields returned, giving the agent a realistic picture of the tool's behavior without contradicting 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?

The description is front-loaded with the main purpose, then proceeds through fields, null behavior, an example, a key access limitation, and cost. Every sentence adds distinct information and there is no filler or repetition of schema 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?

With no output schema present, the description compensates by enumerating the returned fields and explicitly stating that null means the data is not published. It also covers ordering, anonymous limitations, and quota cost. An agent has enough information to call the tool correctly and interpret its response.

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 parameter semantics already come from the schema: siren has a pattern and examples, and limite has default, minimum, and maximum. The description adds a concrete example object and clarifies null handling, but does not need to explain parameter meanings further. 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?

The description opens with a specific verb and resource: 'Renvoie les derniers comptes annuels déposés d'une société française (SIREN)', and adds the ordering 'du plus récent au plus ancien'. This clearly separates it from sibling tools like propecto_societe or propecto_rechercher_societes, which concern company identity or search rather than annual financial statements.

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 provides useful operational context, such as 'Sans clé API (entrée anonyme), les entreprises individuelles ne sont pas servies' and 'Coût : 1 unité de quota', but it never explicitly states when to prefer this tool over sibling alternatives or when not to use it. The intended use is clear by implication from the financial-statement domain, but no explicit routing 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?

The annotations already carry readOnlyHint=true, and the description is consistent with that — it 'renvoie' (returns) rather than mutates. Beyond the annotations, it discloses the quota cost ('Coût : 1 unité de quota'), which is a genuine behavioral trait not present in structured data. It does not contradict the read-only hint.

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 dense sentence that front-loads the core action before listing return fields. The field enumeration is long but earns its place because there is no output schema, so it is the agent's only source for expected return content. Slightly sprawling, but nothing is 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 carries the full burden of explaining return values, and it does so exhaustively: ~13 fields, document/source links, the public fiche link, input provenance, and cost. For a single-parameter read-only lookup, nothing an agent needs to invoke 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%: the id parameter already has a full description, type, range, and example in the schema. The tool description essentially repeats the same provenance info ('champ id renvoyé par propecto_rechercher_marches') without adding new semantic value beyond the schema, 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 opens with a specific verb+resource pair, "Renvoie le détail complet d'un avis de marché public à partir de son identifiant numérique Propecto," and then enumerates the full set of returned fields (intitulé, acheteur, CPV, montant, dates, attributaire, documents, liens). It also ties itself to propecto_rechercher_marches via the id provenance, distinguishing the detail-fetch role from the search role.

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 context is implied rather than stated: the id is explicitly sourced from propecto_rechercher_marches results, and the cost disclosure ('Coût : 1 unité de quota') adds a practical consideration. However, the description never names sibling alternatives (propecto_societe, propecto_finances, etc.) or gives when-not-to-use exclusions, so the agent must infer the choice.

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, and the description adds useful behavioral context beyond that: the data source (DECP), the detailed return structure, the individual-enterprise exclusion, and the quota cost. It does not cover error cases, but the annotations lower the bar for safety disclosure.

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 dense sentences: purpose, return structure, and exclusions/cost. The output fields are enumerated in a clear list, and there is no filler or repetition of annotation data.

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 carries the full burden of explaining return values, and it does so thoroughly: summary metrics, top buyers, and recent contract fields. It also covers cost and a key exclusion, making it complete enough for correct invocation.

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 baseline is 3. The description adds context about the SIREN-based data matching and an example, but it does not add meaning beyond what the schema already provides for either parameter.

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 opens with a specific verb and resource: 'Liste les marchés publics remportés par une société française' and immediately identifies the key input (SIREN). This clearly distinguishes it from siblings like propecto_rechercher_marches (search) and propecto_marche (single contract).

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 makes the usage context explicit: call it with a French company SIREN to get won public contracts. It also gives a clear exclusion: 'Les entreprises individuelles ne sont pas servies.' It does not name alternative tools, so it stops 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?

With annotations already declaring readOnlyHint=true, the description need not repeat that it is read-only. It adds meaningful behavioral context: it identifies the specific data coverage ('dernier exercice exploitable', 'division NAF', 'tranche de chiffre d'affaires'), states that anonymous access excludes individual companies, discloses the cost (1 quota unit), and explains the output when no comparison is possible. It does not detail pagination or response format, but for a single-id query with no output schema that is a minor 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?

The description is dense and information-packed while remaining under ~90 words. It opens with the main action, lists ratios, explains the output, and finishes with the access limitation and cost. Every sentence adds value; the only slight criticism is that it is a long single paragraph that could be more scannable with bullets or sentence breaks, but it is still well-structured for an API description.

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, single-parameter tool, the description is quite complete: it explains what it compares, how it compares, what the output contains, the access restriction, and the quota cost. The main missing detail is exact output schema/format, but since the tool has no output schema and lists the outputs textually, the description covers the essentials. It could also mention the expected data source or that results are based on the latest available fiscal data, but the description already says 'dernier exercice exploitable'.

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?

Even though schema coverage is 100%, the description adds real meaning to the only parameter: it explains that the SIREN is for a French company, that comparison is by sector/taille, and provides a concrete JSON example. The description thus helps the agent pass a valid SIREN and interpret the response, well beyond the schema's simple pattern and example.

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 ('Compare') and a precise resource (ratios of a French company's last exploitable fiscal year against sector peers by NAF division and, when possible, size bracket). It enumerates the exact ratios and outputs (value, quartiles, position, comparison level, number of comparable companies, or reason for failure). This clearly distinguishes it from the sibling tools (e.g., propecto_finances for raw financials, propecto_marche for market data).

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 effectively explains when to use the tool: when you need a sectoral positioning of a French company's ratios. It also gives a clear exclusion condition: 'Sans clé API (entrée anonyme), les entreprises individuelles ne sont pas servies' – when the user has no API key/anonymous entry. It names sibling tools only implicitly by the function's position among propecto_* tools, but it doesn't explicitly say 'use propecto_finances instead for raw financials'. It is strong on entry requirements and failure modes.

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?

Beyond the readOnlyHint annotation, the description discloses that the call itself consumes 1 unit, which is critical behavioral information for an agent deciding whether to invoke it. It also transparently describes the anonymous/no-key fallback behavior, adding real value beyond the structured 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?

The description is compact and front-loaded: it states what is returned first, then the self-consumption quirk, then the anonymous fallback. Every sentence provides distinct, useful information without repetition or fluff.

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?

Although there is no output schema, the description enumerates the returned data points (plan, daily quota, used units, remaining units) and covers the authentication fallback and unit cost. An agent has everything needed to invoke the 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?

With zero parameters and an empty input schema, the description's statement 'Aucun paramètre' matches the schema exactly. There is nothing more to explain, so the baseline for no-parameter tools 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?

The description clearly states the resource (Propecto API key quota), the action (indicates plan, daily quota, used and remaining units), and explicitly notes there are no parameters. This distinguishes it from sibling tools that operate on companies, markets, finances, etc., so an agent can recognize it uniquely.

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 gives clear context for when this tool applies: checking the API key quota and usage. It also explains the behavior without an API key, which is useful decision-making context. It does not explicitly name alternatives or exclusions, but for a standalone quota endpoint this is not a significant gap.

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 declare readOnlyHint=true, which is consistent with the description's search nature. The description adds valuable behavioral details: it returns active aids only, sorts by recent verification, abbreviates long text to 600 characters, and includes a quota cost of 1 unit. This goes beyond the read-only hint by informing the agent of potential quota impact and output truncation, which is not captured elsewhere.

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 concise and structured: it states the purpose, enumerates filters, specifies output format, and ends with an example and cost. It front-loads the core purpose before listing details. Each sentence earns its place, avoiding redundancy with the schema while providing critical usage 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?

Given the tool's moderate complexity (3 optional params, no output schema), the description is complete: it specifies the output fields, sorting, truncation, and quota cost. The schema covers parameter details. There is no output schema, so the description's explanation of the return format is essential and adequately provided.

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%: each parameter (q, pays, limite) has a description and examples. The tool description adds marginal value by reiterating the semantics in the first sentence ('q (mots cherchés dans le libellé, ...)') and providing a usage example, but since the schema already covers all parameter details, the description doesn't need to compensate. 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?

The description clearly states the tool searches public subsidies for businesses ('Recherche des aides et subventions publiques actives destinées aux entreprises'). It specifies the fields searched and the output structure, distinguishing it from sibling tools like propecto_rechercher_marches which search calls for tenders. The verb 'Recherche' with the resource 'aides' is specific and unambiguous.

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 provides explicit filter examples and usage context ('Exemple: {"q": "innovation", "pays": ["FR"], "limite": 5}'). It clearly indicates that the tool returns active aids only and sorts by most recently verified. While it doesn't explicitly mention when not to use it, the clear focus on aids differentiates it from siblings, and the example demonstrates proper usage.

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?

Goes well beyond the readOnlyHint/openWorldHint annotations: discloses the total-count cap (5 000), the nearest-deadline sort, description truncation to 300 characters, source attribution with original links, and the quota cost (1 unit, plus 1 monthly 'marchés' unit with an API key). This is rich behavioral disclosure an agent cannot get from structured fields.

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 front-loaded: purpose first, then filters, then returns, then pagination and cost. Every clause carries information, though the single long paragraph could be more scannable with explicit separation of filters versus returns.

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 fully documents the return shape (id, intitulé, acheteur, pays, CPV, montant, date limite, date de publication, nature, source, liens) and the pagination/cost model. For a 6-parameter search tool with an optional-only schema, nothing an agent needs 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 the baseline is 3; the description adds value beyond the schema by describing the sort order (tri par date limite la plus proche) and reinforcing the meaning of ouverts, limite, and decalage in context. It largely mirrors the schema, so it does not fully reach 5.

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 (Rechercher) and resource (avis de marchés publics), specifying the scope (appels d'offres, attributions) and that results are aggregated from public sources. It also names the sibling it feeds into (id à passer à propecto_marche), letting an agent distinguish it from the other propecto_* tools.

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 operational context: filters for keyword, country, open notices, and department, plus a note that the returned id is used with propecto_marche. It does not explicitly state when to prefer this over alternatives such as propecto_marches_remportes, so it falls just short of explicit when/when-not 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?

Annotations already mark the tool as read-only. The description adds valuable behavioral context beyond that: it returns a total count, sorts most recent filings first, enumerates the returned fields, mentions conditional SIREN data, and states the quota cost. No contradictions with 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?

The description is front-loaded with the tool's purpose and remains information-dense without padding. The long enumeration of return fields is somewhat heavy, but it is necessary given the absence of an 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?

With no output schema, the description carries the burden of explaining return values, and it does so thoroughly: count, ordering, fields, and cost. It does not mention error cases or empty results, but those are not essential for invoking the 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 description coverage is 100%, so the schema already documents both q and limite. The description repeats the q semantics and provides examples, but adds little beyond what the schema already states; it does not discuss the limite parameter.

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 ('Recherche') and resource ('marques déposées'), and lists the exact search keys: name, holder, or filing number. This clearly distinguishes it from sibling tools like propecto_rechercher_societes and propecto_rechercher_marches.

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 gives clear context: use this tool to search registered trademarks by name, holder, or filing number. It does not explicitly name alternatives or exclusion conditions, but the resource scope is unambiguous enough for an agent to select it correctly.

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?

Beyond the readOnlyHint annotation, the description discloses rich behavioral details: prefix-based name matching, accepted identifier formats, result fields, the 20-result cap, anonymous-mode restrictions on French legal entities, and the quota cost. This substantially exceeds what the annotations and schema alone would convey.

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 dense but each sentence carries useful information, including output fields, use case, examples, limits, and anonymous-mode caveats. The examples and repeated maximum-result mention make it slightly longer than necessary, but it remains well structured and informative.

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?

Despite having no output schema, the description enumerates the returned fields and covers search semantics, limits, anonymous access behavior, quota cost, and the intended follow-up tool. An agent has enough context to invoke the tool correctly and interpret its results.

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?

All parameters are already documented in the schema, so the baseline is 3. The description adds meaningful semantics for 'q' through prefix-matching behavior and concrete examples, and clarifies the country filter and result limits; this extra context justifies a slightly above-baseline score.

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 identifies a specific action and resource: searching European companies by name prefix or identification number. It further clarifies the intended use by stating 'Sert à obtenir l'identifiant à passer ensuite à propecto_societe', distinguishing it from sibling search tools.

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 clearly explains that the tool is for finding a company identifier to pass to propecto_societe, and gives concrete search examples. It does not explicitly enumerate when not to use it compared with sibling tools, but the stated downstream purpose provides solid usage context.

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?

The description adds substantial context beyond the readOnlyHint annotation: it discloses quota cost, anonymous access limitations (no API key: no main manager, no individual companies), and null-value semantics. It also notes invalid identifiers are refused without quota consumption, complementing the schema. No contradiction with 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?

The description is moderately long but well-organized: core function first, then a clear list of output fields, then access caveats, then cost. Each sentence contributes, though the field enumeration could be trimmed. Front-loaded and structured well.

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?

Given no output schema, the description compensates by enumerating all returned fields, null semantics, anonymous limitations, and cost. It also names the response format (SocieteResume). This is sufficient for an agent to invoke and interpret the 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?

The schema already fully documents the parameter (100% coverage) with accepted formats, examples, and validation. The description only adds minor nuance like 'lorsque les données existent' for Belgium, which is not in the schema. Since the schema carries the semantic load, a 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?

The description clearly states that the tool returns a summary sheet (SocieteResume) for a company based on its identifier, listing specific fields and the exact verb 'Renvoie'. It is distinct from siblings like propecto_finances or propecto_marche due to its specific focus on the company summary.

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 provides clear context: use when you have a company identifier (SIREN, SIRET, TVA, BCE) and need the summary. It specifies country formats and data availability caveats. However, it does not explicitly mention alternatives like propecto_rechercher_societes 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.