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

Annotations only cover read-only/idempotent safety, and the description goes far beyond them: it discloses the ranking inputs, that already-planned places are excluded, that the pool is limited to Meridian Dispatch guides so thin towns yield short lists, and what the ranking cannot know. That is exactly the behavioural context an agent needs to interpret results.

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?

Purpose is front-loaded, but the body is one long run-on paragraph packing ranking factors, return fields and caveats into dense clauses. Much of it earns its place, yet it would read far better split into short sentences or bullets.

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 output schema, the description supplies the return shape (why, must_see, distance_miles, description, Meridian Dispatch page), the exclusion rule, and the notes caveat. Nothing an agent needs to call or interpret this tool 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 coverage is 100%, so the baseline is 3. The description restates day-vs-date semantics that the schema already documents and never mentions the limit parameter or its default, so it adds little beyond structured data.

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?

Opens with a specific verb and resource: suggesting places for one day of a signed-in traveller's plan, anchored to that day's hotel. It is clearly distinguishable from siblings like suggest_place or list_nearby because it is day-scoped, plan-scoped and personally ranked.

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?

"Use get_plan first if you need the plan id or the day" and "Needs sign-in" give concrete prerequisites, and it explains when to pass day vs date. It never explicitly contrasts itself with sibling tools (suggest_place, list_nearby), which keeps it below a 5.

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