get_company_profile

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

No annotations exist, so the description carries the full behavioral burden. It does disclose the substantive payload (two joined datasets, MAD-denominated metrics), which is valuable, but it says nothing about behavior when no record matches, whether both parameters are optional or one is required, which parameter wins if both are supplied, or whether the lookup is cached/rate-limited. 'Obtenir' implies a read, but that is inference rather than 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?

Single front-loaded sentence with the purpose stated first and the payload details in a compact parenthetical. It is dense but every clause enumerates a distinct returned field; the only cost is that the long nested list is somewhat harder to scan than a short bulleted structure.

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 compensates by enumerating the returned fields in detail, which is exactly what an agent needs to judge relevance. The remaining gap is operational: no result-miss behavior and no indication of how the two optional parameters combine.

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 (ice, company_query) are already documented with examples and formats, making 3 the baseline. The description adds only that the target may be an 'entreprise ou fournisseur' (i.e., suppliers are in scope too), but gives no guidance on precedence between ICE and name lookup or on ambiguity handling for names.

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 ('Obtenir la fiche 360° complète d'une entreprise ou fournisseur au Maroc') and enumerates the exact contents: legal identity fields (ICE, RC, IF, CNSS, capital MAD) cross-referenced with public-procurement history (total volume won, award count, average discount, top buyers). This makes it immediately distinguishable from siblings like search_tenders, get_buyer_intelligence, or check_regulatory_compliance.

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: the header suggests a full-entity lookup rather than an event search. There is no explicit statement of when to prefer this over check_regulatory_compliance (which likely covers the tax-compliance portion) or get_buyer_intelligence, and no exclusions or prerequisites are given.

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