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

Annotations only cover the safe-read profile (readOnly, idempotent, openWorld), and the description adds substantial non-obvious behavior: Europe/Berlin day semantics with no Z suffix, half-open date ranges, view_options exclusivity, the payload_guide/has_more contract, invoice payment-state caveats ('paid=false proves nothing'), and the untrusted-ERP-text warning. This is exactly the kind of context annotations cannot carry.

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?

Every sentence carries real information and the tool's routing constraint is front-loaded, but the body is a dense interleaved wall of facts with minimal visual structure outside the 'Args:' block. It is efficient in content but heavier than it needs to be.

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 14-parameter search tool with an output schema and rich annotations, the description covers query construction, date semantics, view selection, projection, and invoice-specific caveats, plus pointers to payload_guide and has_more handling. Nothing essential to 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?

Schema description coverage is 0%, so the description must compensate, and it largely does: it enumerates filter ops, explains (i)like vs %x% matching, documents date_field requirements, names per-domain view_options keys (article, ticket, task, shipment, articleSupplySource), and flags additional_properties as expensive. Minor gaps remain for page/sort/correlation_id, but the semantically significant parameters are well covered.

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 ('Search weclapp entities with text and typed filters') and immediately frames the tool against its siblings by naming aggregate_entities (for counts/sums) and get_entity (for a single id). An agent can distinguish it from the other 25 tools without opening a schema.

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?

Explicit routing rules are given ('Counts/sums → aggregate_entities; one id → get_entity'), plus when to use date_preset vs ge/lt filters, when view_options are valid, and when NOT to combine them ('not with filters/date_preset/properties/view/page', 'never combine with view=contract_links'). Alternatives and exclusions are both covered.

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