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

With no annotations present the description carries the full burden, and it does so unusually well: it discloses background phone checking ('a result can appear on a later call, and its absence says nothing'), the 2000-candidate scan cap, post-page filtering of min_contact_score, default ordering, and the exact conditions under which whatsapp_business and website_contacts blocks appear. These are non-obvious behaviors an agent could not infer.

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 text is long but nearly every clause earns its place given zero schema coverage and 26 parameters, and it is front-loaded with the filter contract before the return/behavior detail. It would benefit from list formatting and has minor redundancy (the contact-score explanation is restated twice), keeping it short of a 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?

For a 26-parameter search tool with no annotations and no output schema, the description covers return shape (100 rows/page, ordering), pagination continuation via next_offset, the optional contacts/whatsapp blocks, and the post-filter caveat. Nothing an agent needs in order to call it 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 description coverage is 0% and there are 26 parameters, so the description must compensate, which it largely does: it documents value formats and semantics for cnae/cnae_secao, uf, municipio, municipio_codigo, situacao (with enum values), porte, natureza_juridica, capital bounds, date windows, mei, simples, name_contains, cep, partner_name, include_secondary, include_contacts, and min_contact_score (including the integer/tier duality). Only limit/offset defaults and the full order_by option set are left to the bare 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?

States a specific verb and resource ('Find companies/establishments matching filters') and explicitly distinguishes itself from one sibling by routing 'how many' questions to count_companies. It does not, however, differentiate itself from search_partners or get_company, so the differentiation is incomplete for a family of eight 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?

Provides clear conditional guidance ('Use count_companies for how many questions'), tells the agent that all filters are optional and ANDed, and explains when include_contacts vs min_contact_score apply. It never states when NOT to use this tool versus siblings like get_company or search_partners.

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