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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new behavioral context: it discloses the data-quality semantics of the output ('distingue disponibilidade confirmada de estimativa e receita projetada de realizada'), which tells the agent not to treat estimates as confirmed bookings, and it declares the required scope (opportunities:read) plus current unavailability. It does not describe result ordering logic or list size.

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 purpose is front-loaded in the first sentence, the output-semantics caveat follows, and the scope/risk line is compact metadata. No filler sentences, though the mixed Portuguese prose with English tool names means an English-only agent gets less from the same length.

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 2-parameter read-only aggregator with no output schema, the description adequately covers what the tool produces and how confident to be in each field, and annotations cover the safety profile. What it omits is any explanation of the two input parameters and of what 'prioritized' actually means (ordering criteria, list length), which leaves real ambiguity about how to call it and what to expect.

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?

Two parameters (days, start_date) with 0% schema description coverage, and the description never mentions either the time window or the date format. The agent must infer from the schema's min/max/default and regex alone that these control the look-ahead horizon. This is a clear case where the description should have compensated for the coverage gap and does not.

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 composite verb+resource: it aggregates occupancy gaps (upcoming free nights), Neural insights, and eligible referral programs into a single prioritized list. That framing implicitly separates it from siblings like get_insights, get_occupancy_report, and list_referral_programs, which each return only one of the inputs. It stops short of naming those siblings explicitly, so sibling differentiation is inferred rather than stated.

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 composition of inputs implies when the tool is useful (when you want a synthesized opportunity list rather than raw occupancy or insight data), but there is no explicit when-to-use, when-not-to-use, or named alternative. The 'INDISPONÍVEL nesta autorização' note is a strong operational constraint, but it is a session-level availability flag rather than guidance on choosing this tool over another.

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