DrinkedIn Night Out

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so 'Read-only and free' is largely redundant. What the description genuinely adds is policy-level behavior an agent must obey when acting on the guide: relay validated venues only, invent no details, respect legal drinking age.

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?

A single sentence with a colon-led list covering purpose, contents and constraints, all front-loaded with zero filler. The only weak clause is 'Read-only and free', which restates annotations, but it costs almost nothing.

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 parameters, no output schema and rich annotations, the definition covers what the guide contains and the rules it imposes, which is enough to call it correctly. It does not indicate the guide's shape or length, but that is a minor gap for a static reference tool.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The empty schema with additionalProperties=false is self-explanatory.

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 states a specific resource — a usage guide for the night-out planner — and enumerates its contents (largest places, supported vibes, relaying rules), so an agent knows this is reference material rather than a planning action. It never names the sibling drinkedin_plan_night_out, so the differentiation from the action tool is only implied by the word 'How to use'.

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?

Framing it as 'How to use the night-out planner' plus 'the rules to follow when relaying a plan' strongly implies this should be read before or alongside planning, but there is no explicit 'call this first' or 'use X instead' statement referencing drinkedin_plan_night_out. Usage is inferable but not spelled out.

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

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

Although annotations already declare readOnlyHint, idempotentHint, and openWorldHint, the description adds substantial behavioral context: it discloses that free-text address is sent to OpenStreetMap Nominatim as a ranking rather than confirmation, that walking times are estimates (straight line x 1.3), and that hours and prices are never asserted. It also states the tool is free and requires a legal drinking age notice, which goes beyond what the annotations convey.

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 description is front-loaded with purpose and then moves logically through input selection, ambiguity handling, and caveats. It is somewhat long and repeats the geocoding-service caveat that also appears in the address parameter description, but the length is largely justified by the tool's 17 parameters and open-world behavior.

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?

The description covers the full interaction loop for a complex planning tool: location sourcing, geocoding caveats, ambiguity resolution via needs_input, style/vibe sourcing from the sibling, fallback behaviors like partial and no_coverage, and user-facing disclaimers. With no output schema, it still explains the key response fields like geocoded_as, style_applied, and needs_input choices.

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?

With 17 parameters and only 65% schema description coverage, the description adds critical meaning: latitude/longitude are the most reliable input, address is geocoded only when coordinates are absent, place_key comes from a needs_input answer, near is a label echoed back as near_as_given, style sets default stops and walking limits but not hours or prices, and budget is only a soft hint. These details meaningfully clarify parameter behavior beyond the 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?

The first sentence gives a specific verb and resource: 'Plan a walkable 2-4 stop night out around a place using only venues DrinkedIn has validated.' It also distinguishes itself from the sibling tool by requiring styles and vibes to come from drinkedin_get_guide, so an agent can tell which tool owns route planning.

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 description exhaustively explains when to use coordinates versus address versus place name, including how to interpret 'near me', named areas, and trip destinations, and explicitly says to ask the user when no location exists. It also gives a clear fallback path for ambiguous place names via needs_input and instructs the agent never to guess between choices.

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