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

Beyond annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false), the description discloses a non-obvious behavioral trait: tide data exists only for coastal ports, while freshwater requests return only moon phase and the day's time windows (bestWindows). It also names the bestWindows field, giving the agent expectations about response contents in the absence of an output schema.

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 sentences, each earning its place: what it returns, when to use it, and the freshwater caveat. The purpose is front-loaded in the first sentence and nothing is wasted.

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 4-optional-parameter tool with no output schema, the description covers return contents, call triggers, and the key behavioral caveat, while the fully-covered schema handles input semantics. A minor gap is location resolution priority — which parameter wins when lat/lng, query, and portSlug are all supplied — and behavior for ports not in the enum.

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 each parameter is already documented with examples (lat/lng in decimal degrees, query as 'São Francisco do Sul', portSlug with a reliability note steering agents toward slugs). The description adds only marginal param-level value via the coastal/freshwater caveat, so the baseline 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: 'Condições de pesca de hoje' followed by an explicit output list (tábua de marés, fase da lua, melhores janelas de horário, temperatura da água e tempo). This precisely states what the tool returns and clearly differentiates it from all siblings, which are in the equipment/species/technique/location domains.

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 second sentence gives explicit trigger conditions: use when the user asks about tide, moon, best time to fish today, or whether the day is good. It names no when-not-to-use alternatives, but none of the sibling tools compete in the conditions domain, so the clear context is sufficient.

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